
=== 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)

=== Start adding graph ===
<codes.graph_utils.Dumbbell object at 0x7f7c579486d0>

Train epoch 1
[E 1B0  |    320/60000 (  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')


[E 1B10 |   3520/60000 (  6%) ] Loss: 1.9228 top1= 45.9375
[E 1B20 |   6720/60000 ( 11%) ] Loss: 0.9404 top1= 70.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5364 top1= 82.7224


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5714 top1= 80.2684


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5566 top1= 82.7023

Train epoch 2
[E 2B0  |    320/60000 (  1%) ] Loss: 0.8650 top1= 74.3750
[E 2B10 |   3520/60000 (  6%) ] Loss: 0.5626 top1= 81.2500
[E 2B20 |   6720/60000 ( 11%) ] Loss: 0.4415 top1= 85.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3129 top1= 90.9054


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3184 top1= 90.6851


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3301 top1= 90.3345

Train epoch 3
[E 3B0  |    320/60000 (  1%) ] Loss: 0.3162 top1= 90.3125
[E 3B10 |   3520/60000 (  6%) ] Loss: 0.2492 top1= 91.2500
[E 3B20 |   6720/60000 ( 11%) ] Loss: 0.2706 top1= 91.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2495 top1= 92.5881


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2526 top1= 92.4379


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2604 top1= 92.1474

Train epoch 4
[E 4B0  |    320/60000 (  1%) ] Loss: 0.1733 top1= 95.3125
[E 4B10 |   3520/60000 (  6%) ] Loss: 0.1255 top1= 95.9375
[E 4B20 |   6720/60000 ( 11%) ] Loss: 0.1358 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2245 top1= 93.4595


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2272 top1= 93.3393


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2348 top1= 93.2392

Train epoch 5
[E 5B0  |    320/60000 (  1%) ] Loss: 0.1099 top1= 96.8750
[E 5B10 |   3520/60000 (  6%) ] Loss: 0.0706 top1= 98.1250
[E 5B20 |   6720/60000 ( 11%) ] Loss: 0.0670 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2131 top1= 93.9303


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2324 top1= 93.3494


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2254 top1= 93.5296

Train epoch 6
[E 6B0  |    320/60000 (  1%) ] Loss: 0.0622 top1= 98.4375
[E 6B10 |   3520/60000 (  6%) ] Loss: 0.0365 top1= 98.7500
[E 6B20 |   6720/60000 ( 11%) ] Loss: 0.0302 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2220 top1= 94.1106


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2461 top1= 93.6198


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2223 top1= 93.9804

Train epoch 7
[E 7B0  |    320/60000 (  1%) ] Loss: 0.0336 top1= 99.3750
[E 7B10 |   3520/60000 (  6%) ] Loss: 0.0270 top1= 99.6875
[E 7B20 |   6720/60000 ( 11%) ] Loss: 0.0197 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2256 top1= 94.1306


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2548 top1= 93.4996


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2310 top1= 93.9203

Train epoch 8
[E 8B0  |    320/60000 (  1%) ] Loss: 0.0285 top1= 99.0625
[E 8B10 |   3520/60000 (  6%) ] Loss: 0.0208 top1= 99.3750
[E 8B20 |   6720/60000 ( 11%) ] Loss: 0.0163 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2289 top1= 94.3710


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2556 top1= 93.7400


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2391 top1= 93.9103

Train epoch 9
[E 9B0  |    320/60000 (  1%) ] Loss: 0.0346 top1= 99.3750
[E 9B10 |   3520/60000 (  6%) ] Loss: 0.0214 top1= 99.0625
[E 9B20 |   6720/60000 ( 11%) ] Loss: 0.0076 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2364 top1= 94.3409


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2494 top1= 94.0104


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2531 top1= 93.6999

Train epoch 10
[E10B0  |    320/60000 (  1%) ] Loss: 0.0133 top1=100.0000
[E10B10 |   3520/60000 (  6%) ] Loss: 0.0091 top1=100.0000
[E10B20 |   6720/60000 ( 11%) ] Loss: 0.0131 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2317 top1= 94.5212


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2372 top1= 94.3610


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2523 top1= 93.8301

Train epoch 11
[E11B0  |    320/60000 (  1%) ] Loss: 0.0094 top1= 99.6875
[E11B10 |   3520/60000 (  6%) ] Loss: 0.0078 top1=100.0000
[E11B20 |   6720/60000 ( 11%) ] Loss: 0.0115 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2353 top1= 94.3910


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2571 top1= 94.1607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2520 top1= 94.0204

Train epoch 12
[E12B0  |    320/60000 (  1%) ] Loss: 0.0095 top1=100.0000
[E12B10 |   3520/60000 (  6%) ] Loss: 0.0100 top1=100.0000
[E12B20 |   6720/60000 ( 11%) ] Loss: 0.0073 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2317 top1= 94.7817


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2475 top1= 94.3810


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2395 top1= 94.2808

Train epoch 13
[E13B0  |    320/60000 (  1%) ] Loss: 0.0089 top1=100.0000
[E13B10 |   3520/60000 (  6%) ] Loss: 0.0085 top1= 99.6875
[E13B20 |   6720/60000 ( 11%) ] Loss: 0.0191 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2374 top1= 94.7416


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2568 top1= 94.4511


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2411 top1= 94.3510

Train epoch 14
[E14B0  |    320/60000 (  1%) ] Loss: 0.0067 top1=100.0000
[E14B10 |   3520/60000 (  6%) ] Loss: 0.0026 top1=100.0000
[E14B20 |   6720/60000 ( 11%) ] Loss: 0.0058 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2322 top1= 94.9119


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2384 top1= 94.8217


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2354 top1= 94.6314

Train epoch 15
[E15B0  |    320/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E15B10 |   3520/60000 (  6%) ] Loss: 0.0024 top1=100.0000
[E15B20 |   6720/60000 ( 11%) ] Loss: 0.0030 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2307 top1= 94.9319


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2388 top1= 94.9720


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2337 top1= 94.7516

Train epoch 16
[E16B0  |    320/60000 (  1%) ] Loss: 0.0035 top1=100.0000
[E16B10 |   3520/60000 (  6%) ] Loss: 0.0020 top1=100.0000
[E16B20 |   6720/60000 ( 11%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2329 top1= 94.9419


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2423 top1= 94.9018


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2344 top1= 94.8117

Train epoch 17
[E17B0  |    320/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E17B10 |   3520/60000 (  6%) ] Loss: 0.0024 top1=100.0000
[E17B20 |   6720/60000 ( 11%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2344 top1= 95.0020


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2434 top1= 95.0521


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2350 top1= 94.9018

Train epoch 18
[E18B0  |    320/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E18B10 |   3520/60000 (  6%) ] Loss: 0.0022 top1=100.0000
[E18B20 |   6720/60000 ( 11%) ] Loss: 0.0038 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2350 top1= 95.1222


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2431 top1= 95.0821


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2355 top1= 94.9519

Train epoch 19
[E19B0  |    320/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E19B10 |   3520/60000 (  6%) ] Loss: 0.0026 top1=100.0000
[E19B20 |   6720/60000 ( 11%) ] Loss: 0.0037 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2328 top1= 95.2224


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2346 top1= 95.1923


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2351 top1= 94.9319

Train epoch 20
[E20B0  |    320/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E20B10 |   3520/60000 (  6%) ] Loss: 0.0024 top1=100.0000
[E20B20 |   6720/60000 ( 11%) ] Loss: 0.0034 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2325 top1= 95.2123


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2329 top1= 95.1723


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2352 top1= 95.0321

Train epoch 21
[E21B0  |    320/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E21B10 |   3520/60000 (  6%) ] Loss: 0.0027 top1=100.0000
[E21B20 |   6720/60000 ( 11%) ] Loss: 0.0034 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2325 top1= 95.2123


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2324 top1= 95.2224


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2349 top1= 95.1422

Train epoch 22
[E22B0  |    320/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E22B10 |   3520/60000 (  6%) ] Loss: 0.0029 top1=100.0000
[E22B20 |   6720/60000 ( 11%) ] Loss: 0.0031 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2324 top1= 95.2925


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2315 top1= 95.3325


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2346 top1= 95.2724

Train epoch 23
[E23B0  |    320/60000 (  1%) ] Loss: 0.0033 top1=100.0000
[E23B10 |   3520/60000 (  6%) ] Loss: 0.0028 top1=100.0000
[E23B20 |   6720/60000 ( 11%) ] Loss: 0.0030 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2332 top1= 95.3526


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2324 top1= 95.3125


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2351 top1= 95.2825

Train epoch 24
[E24B0  |    320/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E24B10 |   3520/60000 (  6%) ] Loss: 0.0022 top1=100.0000
[E24B20 |   6720/60000 ( 11%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2345 top1= 95.3425


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2335 top1= 95.3425


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2363 top1= 95.2524

Train epoch 25
[E25B0  |    320/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E25B10 |   3520/60000 (  6%) ] Loss: 0.0019 top1=100.0000
[E25B20 |   6720/60000 ( 11%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2361 top1= 95.3225


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2351 top1= 95.3726


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2378 top1= 95.2324

Train epoch 26
[E26B0  |    320/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E26B10 |   3520/60000 (  6%) ] Loss: 0.0016 top1=100.0000
[E26B20 |   6720/60000 ( 11%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2380 top1= 95.2925


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2369 top1= 95.3726


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2397 top1= 95.2825

Train epoch 27
[E27B0  |    320/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E27B10 |   3520/60000 (  6%) ] Loss: 0.0015 top1=100.0000
[E27B20 |   6720/60000 ( 11%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2400 top1= 95.3225


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2389 top1= 95.3526


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2416 top1= 95.2825

Train epoch 28
[E28B0  |    320/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E28B10 |   3520/60000 (  6%) ] Loss: 0.0013 top1=100.0000
[E28B20 |   6720/60000 ( 11%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2416 top1= 95.3325


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2405 top1= 95.3526


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2432 top1= 95.2825

Train epoch 29
[E29B0  |    320/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E29B10 |   3520/60000 (  6%) ] Loss: 0.0012 top1=100.0000
[E29B20 |   6720/60000 ( 11%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2433 top1= 95.3325


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2422 top1= 95.3526


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2449 top1= 95.2825

Train epoch 30
[E30B0  |    320/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E30B10 |   3520/60000 (  6%) ] Loss: 0.0010 top1=100.0000
[E30B20 |   6720/60000 ( 11%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2449 top1= 95.3425


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2439 top1= 95.3425


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2463 top1= 95.3025

