
=== 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 ByzantineWorker(index=10)
=> Add worker ByzantineWorker(index=11)

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7f03b71437f0>

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.2959 top1= 10.0000

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([4, 8, 8, 6, 9], device='cuda:0')
Worker 1 has targets: tensor([5, 3, 6, 0, 9], device='cuda:0')
Worker 2 has targets: tensor([2, 9, 9, 3, 1], device='cuda:0')
Worker 3 has targets: tensor([6, 9, 8, 1, 2], device='cuda:0')
Worker 4 has targets: tensor([5, 8, 9, 1, 8], device='cuda:0')
Worker 5 has targets: tensor([6, 7, 5, 2, 3], device='cuda:0')
Worker 6 has targets: tensor([3, 2, 8, 7, 9], device='cuda:0')
Worker 7 has targets: tensor([3, 8, 7, 8, 7], device='cuda:0')
Worker 8 has targets: tensor([8, 0, 2, 4, 8], device='cuda:0')
Worker 9 has targets: tensor([5, 3, 4, 6, 3], device='cuda:0')
Worker 10 has targets: tensor([4, 8, 8, 6, 9], device='cuda:0')
Worker 11 has targets: tensor([5, 3, 6, 0, 9], device='cuda:0')


[E 1B10 |   4224/60000 (  7%) ] Loss: 1.9224 top1= 46.5625
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.8763 top1= 72.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5005 top1= 84.1947


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5033 top1= 83.3133


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5492 top1= 83.3934

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.6913 top1= 80.6250
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.4583 top1= 85.3125
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.3949 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3018 top1= 90.9756


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3060 top1= 90.7452


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3270 top1= 90.1943

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.3460 top1= 88.1250
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.2298 top1= 92.8125
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.2519 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2430 top1= 92.8285


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2522 top1= 92.4780


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2591 top1= 92.2376

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.1652 top1= 94.3750
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.1288 top1= 95.3125
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.1407 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2216 top1= 93.4295


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2325 top1= 93.1991


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2353 top1= 92.9087

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.1037 top1= 97.1875
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0628 top1= 97.8125
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.1039 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2417 top1= 93.2492


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2542 top1= 92.8285


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2644 top1= 92.5681

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.1079 top1= 96.2500
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0391 top1= 99.6875
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0375 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2383 top1= 93.4295


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2610 top1= 92.8085


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2655 top1= 92.5481

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0691 top1= 97.8125
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0572 top1= 98.1250
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0413 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2267 top1= 93.8702


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2390 top1= 93.6599


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2502 top1= 93.3093

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0487 top1= 99.0625
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0334 top1= 99.0625
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0237 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2100 top1= 94.5713


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2397 top1= 94.0004


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2161 top1= 94.0304

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0311 top1= 99.0625
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0214 top1= 99.3750
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0293 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2218 top1= 94.2708


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2643 top1= 93.6198


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2431 top1= 93.6198

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0337 top1= 98.7500
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0159 top1= 99.6875
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0133 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2112 top1= 94.8217


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2265 top1= 94.6815


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2270 top1= 94.1506

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0097 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0097 top1=100.0000
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0069 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2171 top1= 94.7316


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2337 top1= 94.5212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2389 top1= 94.0905

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0082 top1=100.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0075 top1= 99.6875
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0049 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2219 top1= 94.7516


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2367 top1= 94.6014


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2176 top1= 94.6514

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0092 top1= 99.6875
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0056 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0040 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2294 top1= 94.7516


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2386 top1= 94.6815


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2268 top1= 94.5813

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0070 top1= 99.6875
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0022 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0054 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2258 top1= 94.9419


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2364 top1= 94.7917


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2229 top1= 94.8217

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0023 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2233 top1= 95.0621


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2313 top1= 95.1422


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2206 top1= 94.9419

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0019 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2257 top1= 95.0621


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2318 top1= 95.1422


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2242 top1= 94.9920

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0021 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0028 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2266 top1= 95.0821


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2311 top1= 95.1422


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2258 top1= 95.0120

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0022 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0029 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2272 top1= 95.1022


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2305 top1= 95.1923


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2270 top1= 95.0821

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0025 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0031 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2274 top1= 95.1422


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2295 top1= 95.1723


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2279 top1= 95.1122

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0027 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0027 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0033 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2277 top1= 95.2123


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2291 top1= 95.2825


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2286 top1= 95.1522

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0030 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0034 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2278 top1= 95.2524


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2282 top1= 95.3125


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2292 top1= 95.1923

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0033 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0031 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2285 top1= 95.2825


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2286 top1= 95.3025


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2298 top1= 95.2224

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0033 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0027 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2305 top1= 95.2925


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2301 top1= 95.3125


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2320 top1= 95.2524

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0027 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0021 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2325 top1= 95.3425


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2317 top1= 95.3726


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2341 top1= 95.2724

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0018 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2345 top1= 95.3225


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2335 top1= 95.3826


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2360 top1= 95.2925

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0015 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2370 top1= 95.3125


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2359 top1= 95.3926


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2385 top1= 95.2524

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0014 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2391 top1= 95.3325


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2381 top1= 95.4026


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2405 top1= 95.2825

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0012 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2411 top1= 95.3526


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2401 top1= 95.4026


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2425 top1= 95.2724

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0011 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2430 top1= 95.3526


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2420 top1= 95.4127


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2443 top1= 95.3025

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2448 top1= 95.3626


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2439 top1= 95.4227


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2460 top1= 95.3225

