
=== 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 ByzantineWorker(index=20)
=> Add worker ByzantineWorker(index=21)

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7f594dd992e0>

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: 1.0341 top1= 61.5625
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3934 top1= 88.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6616 top1= 80.8093


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5892 top1= 49.3590


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9497 top1= 44.2508

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2837 top1= 90.4688
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1899 top1= 93.9062
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1981 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5356 top1= 86.8089


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0734 top1= 49.9800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0676 top1= 45.8433

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1562 top1= 94.6875
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1085 top1= 97.0312
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1438 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4433 top1= 87.5901


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6242 top1= 49.7897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3459 top1= 46.3542

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1274 top1= 95.6250
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0808 top1= 97.5000
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1118 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3828 top1= 88.4515


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3478 top1= 50.2003


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0380 top1= 46.7248

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0974 top1= 97.0312
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0607 top1= 98.4375
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0888 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3439 top1= 89.1326


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1156 top1= 51.4022


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8337 top1= 47.9968

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0698 top1= 98.1250
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0407 top1= 99.2188
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0678 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3194 top1= 89.6234


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9901 top1= 52.6242


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7701 top1= 49.4792

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0503 top1= 99.2188
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0312 top1= 99.3750
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0482 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3082 top1= 89.7837


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9429 top1= 53.8161


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6380 top1= 51.5325

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0392 top1= 99.2188
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0273 top1= 99.3750
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0391 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2951 top1= 90.1542


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8731 top1= 54.6975


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6914 top1= 51.8329

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0326 top1= 99.2188
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0286 top1= 99.0625
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0338 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2938 top1= 90.2444


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7835 top1= 55.5489


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4449 top1= 53.8762

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0321 top1= 99.0625
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0258 top1= 99.6875
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0399 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2749 top1= 90.6050


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7948 top1= 56.6506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7111 top1= 50.3005

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0494 top1= 98.4375
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0159 top1= 99.6875
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0258 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2718 top1= 91.0256


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7068 top1= 57.7524


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5442 top1= 52.9647

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0253 top1= 99.5312
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0200 top1= 99.2188
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0146 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2641 top1= 91.1258


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5322 top1= 58.9042


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5800 top1= 53.5757

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0187 top1= 99.2188
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0167 top1= 99.6875
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0319 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2478 top1= 91.7869


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4722 top1= 59.9159


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3516 top1= 55.6991

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0114 top1= 99.8438
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0181 top1= 99.5312
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0163 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2445 top1= 92.0573


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8521 top1= 58.5236


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2834 top1= 58.0228

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0066 top1=100.0000
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0065 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0161 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2397 top1= 92.2175


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5234 top1= 59.6554


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0427 top1= 60.0060

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0077 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0092 top1= 99.6875
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0113 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2415 top1= 92.2977


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3351 top1= 60.5669


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0110 top1= 60.8974

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0082 top1= 99.8438
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0052 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0079 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2294 top1= 92.7684


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4499 top1= 61.1478


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1019 top1= 60.0861

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0058 top1= 99.8438
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0048 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0041 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2292 top1= 92.8085


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1224 top1= 62.6502


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9066 top1= 62.7604

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0031 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0043 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2292 top1= 92.9287


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0893 top1= 62.9708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7992 top1= 64.3630

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0027 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0034 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2289 top1= 93.0689


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0093 top1= 63.7119


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7132 top1= 65.1042

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0022 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2299 top1= 93.0789


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9846 top1= 64.1526


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6935 top1= 66.1458

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0020 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2321 top1= 92.8686


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9388 top1= 64.8538


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7472 top1= 66.3762

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0020 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2313 top1= 93.0188


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9026 top1= 65.4948


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6844 top1= 67.3878

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2318 top1= 93.1891


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8518 top1= 66.1458


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6256 top1= 68.0990

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2341 top1= 93.0889


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7988 top1= 66.9071


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6178 top1= 68.6899

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2346 top1= 93.1290


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7670 top1= 67.4880


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5922 top1= 69.4010

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2353 top1= 93.1490


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7438 top1= 67.8986


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5659 top1= 69.8317

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2361 top1= 93.1791


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7185 top1= 68.3594


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5530 top1= 70.3325

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2368 top1= 93.2192


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6970 top1= 68.7500


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5361 top1= 70.7131

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0012 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2376 top1= 93.1991


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6701 top1= 69.1607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5240 top1= 71.2139

