
=== 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 0x7fae436376d0>

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: 2.1274 top1= 35.3125
[E 1B20 |   6720/60000 ( 11%) ] Loss: 1.7649 top1= 50.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1819 top1= 76.7328


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1752 top1= 77.8245


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1880 top1= 75.2003

Train epoch 2
[E 2B0  |    320/60000 (  1%) ] Loss: 1.3109 top1= 62.8125
[E 2B10 |   3520/60000 (  6%) ] Loss: 0.9175 top1= 71.5625
[E 2B20 |   6720/60000 ( 11%) ] Loss: 0.7722 top1= 77.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5493 top1= 85.8474


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5361 top1= 86.2079


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5608 top1= 85.3265

Train epoch 3
[E 3B0  |    320/60000 (  1%) ] Loss: 0.7031 top1= 80.6250
[E 3B10 |   3520/60000 (  6%) ] Loss: 0.5669 top1= 84.0625
[E 3B20 |   6720/60000 ( 11%) ] Loss: 0.5218 top1= 83.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4189 top1= 88.4515


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4157 top1= 88.4415


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4256 top1= 88.3814

Train epoch 4
[E 4B0  |    320/60000 (  1%) ] Loss: 0.5410 top1= 82.1875
[E 4B10 |   3520/60000 (  6%) ] Loss: 0.4250 top1= 85.9375
[E 4B20 |   6720/60000 ( 11%) ] Loss: 0.4167 top1= 86.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3573 top1= 90.0741


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3581 top1= 89.8738


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3611 top1= 90.1843

Train epoch 5
[E 5B0  |    320/60000 (  1%) ] Loss: 0.3870 top1= 89.6875
[E 5B10 |   3520/60000 (  6%) ] Loss: 0.3082 top1= 93.7500
[E 5B20 |   6720/60000 ( 11%) ] Loss: 0.2980 top1= 90.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3286 top1= 90.5649


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3292 top1= 90.3345


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3292 top1= 90.3746

Train epoch 6
[E 6B0  |    320/60000 (  1%) ] Loss: 0.3039 top1= 92.5000
[E 6B10 |   3520/60000 (  6%) ] Loss: 0.2504 top1= 94.6875
[E 6B20 |   6720/60000 ( 11%) ] Loss: 0.2517 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3012 top1= 91.4062


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3006 top1= 91.1759


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3102 top1= 91.0357

Train epoch 7
[E 7B0  |    320/60000 (  1%) ] Loss: 0.2552 top1= 93.4375
[E 7B10 |   3520/60000 (  6%) ] Loss: 0.1950 top1= 95.3125
[E 7B20 |   6720/60000 ( 11%) ] Loss: 0.2117 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2800 top1= 91.6967


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2856 top1= 91.6466


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2786 top1= 91.8269

Train epoch 8
[E 8B0  |    320/60000 (  1%) ] Loss: 0.1761 top1= 95.3125
[E 8B10 |   3520/60000 (  6%) ] Loss: 0.2888 top1= 92.1875
[E 8B20 |   6720/60000 ( 11%) ] Loss: 0.1745 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2649 top1= 92.1975


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2680 top1= 92.0773


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2655 top1= 92.2276

Train epoch 9
[E 9B0  |    320/60000 (  1%) ] Loss: 0.1445 top1= 95.6250
[E 9B10 |   3520/60000 (  6%) ] Loss: 0.1392 top1= 97.5000
[E 9B20 |   6720/60000 ( 11%) ] Loss: 0.1365 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2555 top1= 92.3978


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2608 top1= 92.2776


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2546 top1= 92.3978

Train epoch 10
[E10B0  |    320/60000 (  1%) ] Loss: 0.1362 top1= 96.2500
[E10B10 |   3520/60000 (  6%) ] Loss: 0.1351 top1= 97.5000
[E10B20 |   6720/60000 ( 11%) ] Loss: 0.1407 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2417 top1= 92.8586


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2443 top1= 92.8586


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2448 top1= 92.8185

Train epoch 11
[E11B0  |    320/60000 (  1%) ] Loss: 0.1232 top1= 96.2500
[E11B10 |   3520/60000 (  6%) ] Loss: 0.1309 top1= 97.5000
[E11B20 |   6720/60000 ( 11%) ] Loss: 0.1200 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2336 top1= 93.1090


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2348 top1= 93.0288


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2340 top1= 92.9587

Train epoch 12
[E12B0  |    320/60000 (  1%) ] Loss: 0.1214 top1= 97.1875
[E12B10 |   3520/60000 (  6%) ] Loss: 0.1013 top1= 97.8125
[E12B20 |   6720/60000 ( 11%) ] Loss: 0.0880 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2263 top1= 93.1691


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2282 top1= 93.1390


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2263 top1= 93.0589

Train epoch 13
[E13B0  |    320/60000 (  1%) ] Loss: 0.0878 top1= 98.1250
[E13B10 |   3520/60000 (  6%) ] Loss: 0.0685 top1= 99.0625
[E13B20 |   6720/60000 ( 11%) ] Loss: 0.0819 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2223 top1= 93.2392


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2225 top1= 93.3494


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2212 top1= 93.3193

Train epoch 14
[E14B0  |    320/60000 (  1%) ] Loss: 0.0449 top1= 99.6875
[E14B10 |   3520/60000 (  6%) ] Loss: 0.0480 top1= 99.0625
[E14B20 |   6720/60000 ( 11%) ] Loss: 0.0722 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2203 top1= 93.2292


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2208 top1= 93.4095


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2203 top1= 93.2392

Train epoch 15
[E15B0  |    320/60000 (  1%) ] Loss: 0.0713 top1= 98.4375
[E15B10 |   3520/60000 (  6%) ] Loss: 0.0677 top1= 99.0625
[E15B20 |   6720/60000 ( 11%) ] Loss: 0.0717 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2100 top1= 93.6498


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2124 top1= 93.6599


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2094 top1= 93.6999

Train epoch 16
[E16B0  |    320/60000 (  1%) ] Loss: 0.0611 top1= 99.3750
[E16B10 |   3520/60000 (  6%) ] Loss: 0.0553 top1= 98.7500
[E16B20 |   6720/60000 ( 11%) ] Loss: 0.0523 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2070 top1= 93.7099


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2028 top1= 93.9203


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2122 top1= 93.6498

Train epoch 17
[E17B0  |    320/60000 (  1%) ] Loss: 0.0506 top1= 99.0625
[E17B10 |   3520/60000 (  6%) ] Loss: 0.0557 top1= 98.7500
[E17B20 |   6720/60000 ( 11%) ] Loss: 0.0503 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2024 top1= 93.8802


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2046 top1= 93.8001


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2020 top1= 93.9002

Train epoch 18
[E18B0  |    320/60000 (  1%) ] Loss: 0.0542 top1= 99.6875
[E18B10 |   3520/60000 (  6%) ] Loss: 0.0444 top1=100.0000
[E18B20 |   6720/60000 ( 11%) ] Loss: 0.0416 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1957 top1= 94.1406


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1976 top1= 94.0204


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1944 top1= 94.1907

Train epoch 19
[E19B0  |    320/60000 (  1%) ] Loss: 0.0436 top1= 99.6875
[E19B10 |   3520/60000 (  6%) ] Loss: 0.0511 top1= 99.0625
[E19B20 |   6720/60000 ( 11%) ] Loss: 0.0422 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1957 top1= 94.1106


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1959 top1= 94.1907


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1934 top1= 94.1006

Train epoch 20
[E20B0  |    320/60000 (  1%) ] Loss: 0.0203 top1=100.0000
[E20B10 |   3520/60000 (  6%) ] Loss: 0.0197 top1=100.0000
[E20B20 |   6720/60000 ( 11%) ] Loss: 0.0288 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1983 top1= 93.9904


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1951 top1= 94.1807


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2009 top1= 93.9103

Train epoch 21
[E21B0  |    320/60000 (  1%) ] Loss: 0.0286 top1= 99.6875
[E21B10 |   3520/60000 (  6%) ] Loss: 0.0436 top1= 99.0625
[E21B20 |   6720/60000 ( 11%) ] Loss: 0.0417 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1967 top1= 94.0705


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1995 top1= 93.9704


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1960 top1= 94.1907

Train epoch 22
[E22B0  |    320/60000 (  1%) ] Loss: 0.0459 top1= 99.3750
[E22B10 |   3520/60000 (  6%) ] Loss: 0.0473 top1= 98.7500
[E22B20 |   6720/60000 ( 11%) ] Loss: 0.0276 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1893 top1= 94.3810


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1856 top1= 94.4511


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1923 top1= 94.2708

Train epoch 23
[E23B0  |    320/60000 (  1%) ] Loss: 0.0313 top1= 99.6875
[E23B10 |   3520/60000 (  6%) ] Loss: 0.0411 top1= 99.3750
[E23B20 |   6720/60000 ( 11%) ] Loss: 0.0377 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1821 top1= 94.4411


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1800 top1= 94.5613


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1843 top1= 94.3510

Train epoch 24
[E24B0  |    320/60000 (  1%) ] Loss: 0.0382 top1= 99.6875
[E24B10 |   3520/60000 (  6%) ] Loss: 0.0298 top1= 99.3750
[E24B20 |   6720/60000 ( 11%) ] Loss: 0.0232 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1834 top1= 94.4812


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1880 top1= 94.4211


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1818 top1= 94.4311

Train epoch 25
[E25B0  |    320/60000 (  1%) ] Loss: 0.0384 top1= 99.0625
[E25B10 |   3520/60000 (  6%) ] Loss: 0.0293 top1= 99.3750
[E25B20 |   6720/60000 ( 11%) ] Loss: 0.0317 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1800 top1= 94.5012


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1803 top1= 94.5312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1788 top1= 94.5813

Train epoch 26
[E26B0  |    320/60000 (  1%) ] Loss: 0.0111 top1=100.0000
[E26B10 |   3520/60000 (  6%) ] Loss: 0.0103 top1=100.0000
[E26B20 |   6720/60000 ( 11%) ] Loss: 0.0128 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1866 top1= 94.3409


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1954 top1= 94.1006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1847 top1= 94.6514

Train epoch 27
[E27B0  |    320/60000 (  1%) ] Loss: 0.0574 top1= 98.4375
[E27B10 |   3520/60000 (  6%) ] Loss: 0.0198 top1=100.0000
[E27B20 |   6720/60000 ( 11%) ] Loss: 0.0285 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1785 top1= 94.7216


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1797 top1= 94.7716


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1788 top1= 94.7616

Train epoch 28
[E28B0  |    320/60000 (  1%) ] Loss: 0.0204 top1= 99.6875
[E28B10 |   3520/60000 (  6%) ] Loss: 0.0230 top1= 99.6875
[E28B20 |   6720/60000 ( 11%) ] Loss: 0.0184 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1816 top1= 94.5413


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1835 top1= 94.6414


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1830 top1= 94.4912

Train epoch 29
[E29B0  |    320/60000 (  1%) ] Loss: 0.0266 top1= 99.6875
[E29B10 |   3520/60000 (  6%) ] Loss: 0.0157 top1=100.0000
[E29B20 |   6720/60000 ( 11%) ] Loss: 0.0176 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1721 top1= 94.8317


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1684 top1= 94.9519


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1756 top1= 94.7516

Train epoch 30
[E30B0  |    320/60000 (  1%) ] Loss: 0.0227 top1= 99.6875
[E30B10 |   3520/60000 (  6%) ] Loss: 0.0226 top1= 99.3750
[E30B20 |   6720/60000 ( 11%) ] Loss: 0.0184 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1731 top1= 94.7316


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1764 top1= 94.7115


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1720 top1= 94.7917

