
=== 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 BitFlippingWorker
=> Add worker BitFlippingWorker

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7f31e74a87f0>

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: 1.9321 top1= 45.0000
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.8874 top1= 71.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5058 top1= 84.0445


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4941 top1= 83.8141


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5538 top1= 83.0529

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.6940 top1= 80.3125
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.4777 top1= 83.1250
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.3832 top1= 89.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3060 top1= 90.9756


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3076 top1= 90.9054


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3303 top1= 90.2043

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.3546 top1= 88.4375
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.2526 top1= 91.8750
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.2597 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2523 top1= 92.6082


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2555 top1= 92.3878


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2636 top1= 92.1174

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.1889 top1= 94.6875
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.1499 top1= 95.9375
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.1612 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2216 top1= 93.3293


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2322 top1= 92.9788


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2349 top1= 92.8385

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.1315 top1= 95.6250
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0776 top1= 97.8125
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.1135 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2280 top1= 93.5096


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2418 top1= 93.0689


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2408 top1= 93.1591

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0772 top1= 98.1250
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0623 top1= 97.8125
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0662 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2365 top1= 93.4095


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2572 top1= 92.8385


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2433 top1= 93.4996

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0890 top1= 96.8750
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0641 top1= 97.1875
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0280 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2299 top1= 93.6498


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2419 top1= 93.1591


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2505 top1= 93.2592

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0420 top1= 98.7500
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0383 top1= 99.0625
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0269 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2163 top1= 94.2007


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2293 top1= 93.7800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2300 top1= 93.7200

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0219 top1= 99.6875
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0337 top1= 98.4375
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0248 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2237 top1= 94.1607


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2557 top1= 93.6298


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2302 top1= 93.9804

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0518 top1= 98.4375
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0214 top1= 99.3750
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0146 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2107 top1= 94.5913


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2269 top1= 94.3009


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2142 top1= 94.4812

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0145 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0204 top1= 99.3750
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0100 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2194 top1= 94.4411


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2324 top1= 94.2208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2357 top1= 93.9203

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0134 top1= 99.6875
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0070 top1=100.0000
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0072 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2239 top1= 94.4010


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2337 top1= 94.4311


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2360 top1= 93.8702

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0068 top1=100.0000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0078 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0061 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2333 top1= 94.3810


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2409 top1= 94.3610


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2309 top1= 94.2308

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0072 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0033 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0046 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2362 top1= 94.4511


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2409 top1= 94.4311


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2357 top1= 94.2708

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0032 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0013 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0039 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2355 top1= 94.6314


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2381 top1= 94.5513


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2381 top1= 94.2909

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0012 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2354 top1= 94.6114


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2408 top1= 94.5813


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2325 top1= 94.5012

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2388 top1= 94.6615


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2439 top1= 94.5813


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2359 top1= 94.5112

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0008 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2419 top1= 94.6214


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2468 top1= 94.5713


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2391 top1= 94.5112

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0007 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2445 top1= 94.6214


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2493 top1= 94.5913


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2417 top1= 94.5112

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0006 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2470 top1= 94.6214


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2517 top1= 94.5713


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2441 top1= 94.5212

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0006 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2491 top1= 94.6114


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2539 top1= 94.5713


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2462 top1= 94.5112

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2512 top1= 94.6114


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2559 top1= 94.5613


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2482 top1= 94.5112

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2531 top1= 94.5913


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2577 top1= 94.5513


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2500 top1= 94.5112

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0004 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2549 top1= 94.6014


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2595 top1= 94.5513


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2518 top1= 94.5312

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0004 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2565 top1= 94.6014


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2611 top1= 94.5613


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2534 top1= 94.5312

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0004 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2582 top1= 94.5913


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2627 top1= 94.5713


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2551 top1= 94.5312

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0004 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2597 top1= 94.6014


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2642 top1= 94.5713


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2566 top1= 94.5312

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0003 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2611 top1= 94.6014


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2656 top1= 94.5613


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2579 top1= 94.5312

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0003 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2625 top1= 94.6014


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2669 top1= 94.5613


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2593 top1= 94.5312

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0003 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2638 top1= 94.5713


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2682 top1= 94.5613


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2606 top1= 94.5312

