
=== 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 0x7f965f0142b0>

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: 1.1768 top1= 59.0625
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.4079 top1= 85.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6956 top1= 82.5321


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2897 top1= 49.0885


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7964 top1= 43.6298

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2905 top1= 90.4688
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.2332 top1= 93.7500
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.2599 top1= 92.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6307 top1= 84.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4827 top1= 49.5493


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8382 top1= 45.2224

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.2412 top1= 91.7188
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1813 top1= 95.4688
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.2042 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5624 top1= 85.8974


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2851 top1= 49.9800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7062 top1= 45.7532

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1993 top1= 93.4375
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1665 top1= 95.3125
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1837 top1= 94.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5392 top1= 86.2380


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2079 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6648 top1= 45.9335

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1842 top1= 94.2188
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1547 top1= 96.0938
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.1684 top1= 94.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5343 top1= 86.0477


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1669 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6528 top1= 45.9736

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1738 top1= 94.5312
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1454 top1= 96.0938
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1564 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5263 top1= 86.2881


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1559 top1= 50.8313


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6310 top1= 45.8133

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.1655 top1= 94.5312
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1378 top1= 96.4062
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.1484 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5238 top1= 86.2179


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1528 top1= 50.9115


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6164 top1= 45.7131

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1597 top1= 94.8438
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1337 top1= 97.0312
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1413 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5211 top1= 86.3081


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1524 top1= 50.8714


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6050 top1= 45.6731

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1561 top1= 95.1562
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1263 top1= 97.0312
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1384 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5204 top1= 86.1178


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1373 top1= 50.7712


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6184 top1= 45.8133

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1505 top1= 95.6250
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.1238 top1= 97.0312
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1356 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5171 top1= 86.2480


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1282 top1= 50.8013


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6015 top1= 45.8433

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1479 top1= 95.6250
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.1215 top1= 97.5000
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1332 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5192 top1= 86.3081


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1240 top1= 50.7712


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6109 top1= 45.7833

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1468 top1= 95.9375
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.1193 top1= 97.5000
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.1304 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5202 top1= 85.9175


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1245 top1= 50.8013


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6304 top1= 45.6731

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1460 top1= 95.4688
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.1163 top1= 97.5000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1293 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5212 top1= 86.0877


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1345 top1= 50.7612


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6273 top1= 45.6030

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.1433 top1= 96.0938
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.1136 top1= 97.0312
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.1264 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5220 top1= 86.2480


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1231 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5825 top1= 45.6130

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.1413 top1= 95.7812
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.1152 top1= 97.0312
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.1285 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5268 top1= 86.1579


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1217 top1= 50.6310


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5762 top1= 45.4728

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.1461 top1= 95.3125
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.1187 top1= 96.8750
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.1353 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5249 top1= 86.0477


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1120 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5833 top1= 45.4427

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.1475 top1= 95.1562
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.1261 top1= 96.4062
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.1415 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5216 top1= 86.3582


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1292 top1= 50.5308


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5321 top1= 45.6831

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.1417 top1= 95.3125
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.1235 top1= 96.5625
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.1413 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5172 top1= 86.5284


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1514 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5848 top1= 45.8934

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.1292 top1= 96.4062
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.1196 top1= 96.7188
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.1407 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5088 top1= 86.7889


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1718 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5401 top1= 45.9635

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.1217 top1= 96.5625
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.1165 top1= 96.5625
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.1302 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5040 top1= 86.9291


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1995 top1= 50.2404


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4621 top1= 46.1639

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.1172 top1= 97.0312
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.1146 top1= 96.5625
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.1290 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5030 top1= 86.9091


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1922 top1= 50.1202


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3994 top1= 46.3442

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.1169 top1= 97.3438
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.1215 top1= 96.0938
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.1284 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5077 top1= 86.8890


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2087 top1= 50.0100


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3455 top1= 46.5044

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.1250 top1= 96.7188
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.1255 top1= 96.2500
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.1157 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5027 top1= 87.5701


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2088 top1= 50.0200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4860 top1= 46.3141

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.1257 top1= 96.2500
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.1173 top1= 96.4062
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.1208 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5166 top1= 86.8690


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1733 top1= 49.9499


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4254 top1= 46.2941

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.1303 top1= 95.9375
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.1099 top1= 97.0312
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.1310 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5189 top1= 86.6386


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1672 top1= 49.8998


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4328 top1= 46.3842

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.1235 top1= 96.2500
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.1082 top1= 97.1875
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.1206 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5191 top1= 86.7087


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1258 top1= 50.1002


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4536 top1= 46.3341

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.1253 top1= 96.4062
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.1044 top1= 97.5000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.1151 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5298 top1= 85.3966


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1110 top1= 50.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5767 top1= 45.7232

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.1474 top1= 95.9375
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.1083 top1= 97.1875
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.1248 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5342 top1= 85.0060


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1078 top1= 50.5108


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5726 top1= 45.7232

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.1396 top1= 95.7812
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.1130 top1= 97.0312
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.1279 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5378 top1= 85.0461


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1015 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6060 top1= 45.3025

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.1440 top1= 95.4688
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.1102 top1= 97.0312
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.1430 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5303 top1= 85.6270


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1069 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5935 top1= 45.7332

