
📌S Retain class distribution for seed 9:
Class 0: 5323
Class 1: 6142
Class 2: 5358
Class 3: 5531
Class 4: 5242
Class 5: 4821
Class 6: 5318
Class 7: 5665
Class 8: 5251
Class 9: 5349

📌S Forget class distribution for seed 9:
Class 0: 600
Class 1: 600
Class 2: 600
Class 3: 600
Class 4: 600
Class 5: 600
Class 6: 600
Class 7: 600
Class 8: 600
Class 9: 600
790

📊 Updated class distribution:
Retain set:
  Class 0: 5773
  Class 1: 6592
  Class 2: 5808
  Class 3: 5981
  Class 4: 5692
  Class 5: 5271
  Class 6: 5768
  Class 7: 6115
  Class 8: 5701
  Class 9: 5799
Forget set:
  Class 0: 150
  Class 1: 150
  Class 2: 150
  Class 3: 150
  Class 4: 150
  Class 5: 150
  Class 6: 150
  Class 7: 150
  Class 8: 150
  Class 9: 150
⚠️ Warning: Retain train loader may not be shuffled.
Training Epoch: 1 [256/58500]	Loss: 2.3152	LR: 0.000000
Training Epoch: 1 [512/58500]	Loss: 2.2999	LR: 0.000437
Training Epoch: 1 [768/58500]	Loss: 2.2933	LR: 0.000873
Training Epoch: 1 [1024/58500]	Loss: 2.3098	LR: 0.001310
Training Epoch: 1 [1280/58500]	Loss: 2.2982	LR: 0.001747
Training Epoch: 1 [1536/58500]	Loss: 2.2872	LR: 0.002183
Training Epoch: 1 [1792/58500]	Loss: 2.3011	LR: 0.002620
Training Epoch: 1 [2048/58500]	Loss: 2.2632	LR: 0.003057
Training Epoch: 1 [2304/58500]	Loss: 2.2593	LR: 0.003493
Training Epoch: 1 [2560/58500]	Loss: 2.2374	LR: 0.003930
Training Epoch: 1 [2816/58500]	Loss: 2.2399	LR: 0.004367
Training Epoch: 1 [3072/58500]	Loss: 2.2241	LR: 0.004803
Training Epoch: 1 [3328/58500]	Loss: 2.2046	LR: 0.005240
Training Epoch: 1 [3584/58500]	Loss: 2.2088	LR: 0.005677
Training Epoch: 1 [3840/58500]	Loss: 2.1813	LR: 0.006114
Training Epoch: 1 [4096/58500]	Loss: 2.1556	LR: 0.006550
Training Epoch: 1 [4352/58500]	Loss: 2.1420	LR: 0.006987
Training Epoch: 1 [4608/58500]	Loss: 2.0981	LR: 0.007424
Training Epoch: 1 [4864/58500]	Loss: 2.1123	LR: 0.007860
Training Epoch: 1 [5120/58500]	Loss: 2.0915	LR: 0.008297
Training Epoch: 1 [5376/58500]	Loss: 2.0657	LR: 0.008734
Training Epoch: 1 [5632/58500]	Loss: 2.0789	LR: 0.009170
Training Epoch: 1 [5888/58500]	Loss: 1.9780	LR: 0.009607
Training Epoch: 1 [6144/58500]	Loss: 1.9786	LR: 0.010044
Training Epoch: 1 [6400/58500]	Loss: 1.9082	LR: 0.010480
Training Epoch: 1 [6656/58500]	Loss: 1.9213	LR: 0.010917
Training Epoch: 1 [6912/58500]	Loss: 1.9122	LR: 0.011354
Training Epoch: 1 [7168/58500]	Loss: 1.8509	LR: 0.011790
Training Epoch: 1 [7424/58500]	Loss: 1.8602	LR: 0.012227
Training Epoch: 1 [7680/58500]	Loss: 1.7305	LR: 0.012664
Training Epoch: 1 [7936/58500]	Loss: 1.7572	LR: 0.013100
Training Epoch: 1 [8192/58500]	Loss: 1.7159	LR: 0.013537
Training Epoch: 1 [8448/58500]	Loss: 1.6197	LR: 0.013974
Training Epoch: 1 [8704/58500]	Loss: 1.6193	LR: 0.014410
Training Epoch: 1 [8960/58500]	Loss: 1.5946	LR: 0.014847
Training Epoch: 1 [9216/58500]	Loss: 1.5582	LR: 0.015284
Training Epoch: 1 [9472/58500]	Loss: 1.4426	LR: 0.015721
Training Epoch: 1 [9728/58500]	Loss: 1.4475	LR: 0.016157
Training Epoch: 1 [9984/58500]	Loss: 1.3836	LR: 0.016594
Training Epoch: 1 [10240/58500]	Loss: 1.2926	LR: 0.017031
Training Epoch: 1 [10496/58500]	Loss: 1.2453	LR: 0.017467
Training Epoch: 1 [10752/58500]	Loss: 1.1699	LR: 0.017904
Training Epoch: 1 [11008/58500]	Loss: 1.1681	LR: 0.018341
Training Epoch: 1 [11264/58500]	Loss: 1.0993	LR: 0.018777
Training Epoch: 1 [11520/58500]	Loss: 1.0608	LR: 0.019214
Training Epoch: 1 [11776/58500]	Loss: 0.9960	LR: 0.019651
Training Epoch: 1 [12032/58500]	Loss: 0.9741	LR: 0.020087
Training Epoch: 1 [12288/58500]	Loss: 0.9090	LR: 0.020524
Training Epoch: 1 [12544/58500]	Loss: 0.8016	LR: 0.020961
Training Epoch: 1 [12800/58500]	Loss: 0.7930	LR: 0.021397
Training Epoch: 1 [13056/58500]	Loss: 0.7713	LR: 0.021834
Training Epoch: 1 [13312/58500]	Loss: 0.7226	LR: 0.022271
Training Epoch: 1 [13568/58500]	Loss: 0.7117	LR: 0.022707
Training Epoch: 1 [13824/58500]	Loss: 0.6375	LR: 0.023144
Training Epoch: 1 [14080/58500]	Loss: 0.5605	LR: 0.023581
Training Epoch: 1 [14336/58500]	Loss: 0.6146	LR: 0.024017
Training Epoch: 1 [14592/58500]	Loss: 0.4881	LR: 0.024454
Training Epoch: 1 [14848/58500]	Loss: 0.5166	LR: 0.024891
Training Epoch: 1 [15104/58500]	Loss: 0.4085	LR: 0.025328
Training Epoch: 1 [15360/58500]	Loss: 0.4528	LR: 0.025764
Training Epoch: 1 [15616/58500]	Loss: 0.4068	LR: 0.026201
Training Epoch: 1 [15872/58500]	Loss: 0.3815	LR: 0.026638
Training Epoch: 1 [16128/58500]	Loss: 0.3984	LR: 0.027074
Training Epoch: 1 [16384/58500]	Loss: 0.3236	LR: 0.027511
Training Epoch: 1 [16640/58500]	Loss: 0.3882	LR: 0.027948
Training Epoch: 1 [16896/58500]	Loss: 0.3315	LR: 0.028384
Training Epoch: 1 [17152/58500]	Loss: 0.2924	LR: 0.028821
Training Epoch: 1 [17408/58500]	Loss: 0.2590	LR: 0.029258
Training Epoch: 1 [17664/58500]	Loss: 0.2490	LR: 0.029694
Training Epoch: 1 [17920/58500]	Loss: 0.2366	LR: 0.030131
Training Epoch: 1 [18176/58500]	Loss: 0.2794	LR: 0.030568
Training Epoch: 1 [18432/58500]	Loss: 0.2029	LR: 0.031004
Training Epoch: 1 [18688/58500]	Loss: 0.2290	LR: 0.031441
Training Epoch: 1 [18944/58500]	Loss: 0.2334	LR: 0.031878
Training Epoch: 1 [19200/58500]	Loss: 0.2313	LR: 0.032314
Training Epoch: 1 [19456/58500]	Loss: 0.1884	LR: 0.032751
Training Epoch: 1 [19712/58500]	Loss: 0.2442	LR: 0.033188
Training Epoch: 1 [19968/58500]	Loss: 0.1597	LR: 0.033624
Training Epoch: 1 [20224/58500]	Loss: 0.1946	LR: 0.034061
Training Epoch: 1 [20480/58500]	Loss: 0.2233	LR: 0.034498
Training Epoch: 1 [20736/58500]	Loss: 0.1539	LR: 0.034934
Training Epoch: 1 [20992/58500]	Loss: 0.1482	LR: 0.035371
Training Epoch: 1 [21248/58500]	Loss: 0.1829	LR: 0.035808
Training Epoch: 1 [21504/58500]	Loss: 0.1698	LR: 0.036245
Training Epoch: 1 [21760/58500]	Loss: 0.1545	LR: 0.036681
Training Epoch: 1 [22016/58500]	Loss: 0.1512	LR: 0.037118
Training Epoch: 1 [22272/58500]	Loss: 0.1592	LR: 0.037555
Training Epoch: 1 [22528/58500]	Loss: 0.1101	LR: 0.037991
Training Epoch: 1 [22784/58500]	Loss: 0.1475	LR: 0.038428
Training Epoch: 1 [23040/58500]	Loss: 0.1297	LR: 0.038865
Training Epoch: 1 [23296/58500]	Loss: 0.1698	LR: 0.039301
Training Epoch: 1 [23552/58500]	Loss: 0.1607	LR: 0.039738
Training Epoch: 1 [23808/58500]	Loss: 0.1363	LR: 0.040175
Training Epoch: 1 [24064/58500]	Loss: 0.1610	LR: 0.040611
Training Epoch: 1 [24320/58500]	Loss: 0.1258	LR: 0.041048
Training Epoch: 1 [24576/58500]	Loss: 0.1556	LR: 0.041485
Training Epoch: 1 [24832/58500]	Loss: 0.1092	LR: 0.041921
Training Epoch: 1 [25088/58500]	Loss: 0.1505	LR: 0.042358
Training Epoch: 1 [25344/58500]	Loss: 0.2061	LR: 0.042795
Training Epoch: 1 [25600/58500]	Loss: 0.1336	LR: 0.043231
Training Epoch: 1 [25856/58500]	Loss: 0.1757	LR: 0.043668
Training Epoch: 1 [26112/58500]	Loss: 0.1622	LR: 0.044105
Training Epoch: 1 [26368/58500]	Loss: 0.1612	LR: 0.044541
Training Epoch: 1 [26624/58500]	Loss: 0.1802	LR: 0.044978
Training Epoch: 1 [26880/58500]	Loss: 0.1566	LR: 0.045415
Training Epoch: 1 [27136/58500]	Loss: 0.1175	LR: 0.045852
Training Epoch: 1 [27392/58500]	Loss: 0.1024	LR: 0.046288
Training Epoch: 1 [27648/58500]	Loss: 0.1535	LR: 0.046725
Training Epoch: 1 [27904/58500]	Loss: 0.1529	LR: 0.047162
Training Epoch: 1 [28160/58500]	Loss: 0.1337	LR: 0.047598
Training Epoch: 1 [28416/58500]	Loss: 0.1150	LR: 0.048035
Training Epoch: 1 [28672/58500]	Loss: 0.1324	LR: 0.048472
Training Epoch: 1 [28928/58500]	Loss: 0.1527	LR: 0.048908
Training Epoch: 1 [29184/58500]	Loss: 0.1077	LR: 0.049345
Training Epoch: 1 [29440/58500]	Loss: 0.1063	LR: 0.049782
Training Epoch: 1 [29696/58500]	Loss: 0.1351	LR: 0.050218
Training Epoch: 1 [29952/58500]	Loss: 0.1287	LR: 0.050655
Training Epoch: 1 [30208/58500]	Loss: 0.1135	LR: 0.051092
Training Epoch: 1 [30464/58500]	Loss: 0.1547	LR: 0.051528
Training Epoch: 1 [30720/58500]	Loss: 0.1695	LR: 0.051965
Training Epoch: 1 [30976/58500]	Loss: 0.0976	LR: 0.052402
Training Epoch: 1 [31232/58500]	Loss: 0.1064	LR: 0.052838
Training Epoch: 1 [31488/58500]	Loss: 0.1194	LR: 0.053275
Training Epoch: 1 [31744/58500]	Loss: 0.1368	LR: 0.053712
Training Epoch: 1 [32000/58500]	Loss: 0.1003	LR: 0.054148
Training Epoch: 1 [32256/58500]	Loss: 0.1200	LR: 0.054585
Training Epoch: 1 [32512/58500]	Loss: 0.1043	LR: 0.055022
Training Epoch: 1 [32768/58500]	Loss: 0.0858	LR: 0.055459
Training Epoch: 1 [33024/58500]	Loss: 0.1122	LR: 0.055895
Training Epoch: 1 [33280/58500]	Loss: 0.0883	LR: 0.056332
Training Epoch: 1 [33536/58500]	Loss: 0.0853	LR: 0.056769
Training Epoch: 1 [33792/58500]	Loss: 0.0840	LR: 0.057205
Training Epoch: 1 [34048/58500]	Loss: 0.0640	LR: 0.057642
Training Epoch: 1 [34304/58500]	Loss: 0.1113	LR: 0.058079
Training Epoch: 1 [34560/58500]	Loss: 0.1146	LR: 0.058515
Training Epoch: 1 [34816/58500]	Loss: 0.1651	LR: 0.058952
Training Epoch: 1 [35072/58500]	Loss: 0.0555	LR: 0.059389
Training Epoch: 1 [35328/58500]	Loss: 0.1005	LR: 0.059825
Training Epoch: 1 [35584/58500]	Loss: 0.0865	LR: 0.060262
Training Epoch: 1 [35840/58500]	Loss: 0.0730	LR: 0.060699
Training Epoch: 1 [36096/58500]	Loss: 0.1539	LR: 0.061135
Training Epoch: 1 [36352/58500]	Loss: 0.1096	LR: 0.061572
Training Epoch: 1 [36608/58500]	Loss: 0.0310	LR: 0.062009
Training Epoch: 1 [36864/58500]	Loss: 0.0925	LR: 0.062445
Training Epoch: 1 [37120/58500]	Loss: 0.1380	LR: 0.062882
Training Epoch: 1 [37376/58500]	Loss: 0.0840	LR: 0.063319
Training Epoch: 1 [37632/58500]	Loss: 0.0871	LR: 0.063755
Training Epoch: 1 [37888/58500]	Loss: 0.1207	LR: 0.064192
Training Epoch: 1 [38144/58500]	Loss: 0.1094	LR: 0.064629
Training Epoch: 1 [38400/58500]	Loss: 0.1517	LR: 0.065066
Training Epoch: 1 [38656/58500]	Loss: 0.1024	LR: 0.065502
Training Epoch: 1 [38912/58500]	Loss: 0.1230	LR: 0.065939
Training Epoch: 1 [39168/58500]	Loss: 0.1184	LR: 0.066376
Training Epoch: 1 [39424/58500]	Loss: 0.0691	LR: 0.066812
Training Epoch: 1 [39680/58500]	Loss: 0.0835	LR: 0.067249
Training Epoch: 1 [39936/58500]	Loss: 0.0943	LR: 0.067686
Training Epoch: 1 [40192/58500]	Loss: 0.1001	LR: 0.068122
Training Epoch: 1 [40448/58500]	Loss: 0.1058	LR: 0.068559
Training Epoch: 1 [40704/58500]	Loss: 0.0919	LR: 0.068996
Training Epoch: 1 [40960/58500]	Loss: 0.1241	LR: 0.069432
Training Epoch: 1 [41216/58500]	Loss: 0.1037	LR: 0.069869
Training Epoch: 1 [41472/58500]	Loss: 0.0970	LR: 0.070306
Training Epoch: 1 [41728/58500]	Loss: 0.0675	LR: 0.070742
Training Epoch: 1 [41984/58500]	Loss: 0.0782	LR: 0.071179
Training Epoch: 1 [42240/58500]	Loss: 0.0971	LR: 0.071616
Training Epoch: 1 [42496/58500]	Loss: 0.0784	LR: 0.072052
Training Epoch: 1 [42752/58500]	Loss: 0.1430	LR: 0.072489
Training Epoch: 1 [43008/58500]	Loss: 0.0425	LR: 0.072926
Training Epoch: 1 [43264/58500]	Loss: 0.0886	LR: 0.073362
Training Epoch: 1 [43520/58500]	Loss: 0.0745	LR: 0.073799
Training Epoch: 1 [43776/58500]	Loss: 0.0786	LR: 0.074236
Training Epoch: 1 [44032/58500]	Loss: 0.1296	LR: 0.074672
Training Epoch: 1 [44288/58500]	Loss: 0.0682	LR: 0.075109
Training Epoch: 1 [44544/58500]	Loss: 0.0952	LR: 0.075546
Training Epoch: 1 [44800/58500]	Loss: 0.0767	LR: 0.075983
Training Epoch: 1 [45056/58500]	Loss: 0.0693	LR: 0.076419
Training Epoch: 1 [45312/58500]	Loss: 0.1005	LR: 0.076856
Training Epoch: 1 [45568/58500]	Loss: 0.1812	LR: 0.077293
Training Epoch: 1 [45824/58500]	Loss: 0.0837	LR: 0.077729
Training Epoch: 1 [46080/58500]	Loss: 0.0763	LR: 0.078166
Training Epoch: 1 [46336/58500]	Loss: 0.1017	LR: 0.078603
Training Epoch: 1 [46592/58500]	Loss: 0.0893	LR: 0.079039
Training Epoch: 1 [46848/58500]	Loss: 0.0637	LR: 0.079476
Training Epoch: 1 [47104/58500]	Loss: 0.1058	LR: 0.079913
Training Epoch: 1 [47360/58500]	Loss: 0.0531	LR: 0.080349
Training Epoch: 1 [47616/58500]	Loss: 0.1325	LR: 0.080786
Training Epoch: 1 [47872/58500]	Loss: 0.0784	LR: 0.081223
Training Epoch: 1 [48128/58500]	Loss: 0.0466	LR: 0.081659
Training Epoch: 1 [48384/58500]	Loss: 0.0756	LR: 0.082096
Training Epoch: 1 [48640/58500]	Loss: 0.1016	LR: 0.082533
Training Epoch: 1 [48896/58500]	Loss: 0.0644	LR: 0.082969
Training Epoch: 1 [49152/58500]	Loss: 0.0505	LR: 0.083406
Training Epoch: 1 [49408/58500]	Loss: 0.0815	LR: 0.083843
Training Epoch: 1 [49664/58500]	Loss: 0.0949	LR: 0.084279
Training Epoch: 1 [49920/58500]	Loss: 0.0617	LR: 0.084716
Training Epoch: 1 [50176/58500]	Loss: 0.0980	LR: 0.085153
Training Epoch: 1 [50432/58500]	Loss: 0.0839	LR: 0.085590
Training Epoch: 1 [50688/58500]	Loss: 0.0587	LR: 0.086026
Training Epoch: 1 [50944/58500]	Loss: 0.0539	LR: 0.086463
Training Epoch: 1 [51200/58500]	Loss: 0.0946	LR: 0.086900
Training Epoch: 1 [51456/58500]	Loss: 0.0827	LR: 0.087336
Training Epoch: 1 [51712/58500]	Loss: 0.0678	LR: 0.087773
Training Epoch: 1 [51968/58500]	Loss: 0.0765	LR: 0.088210
Training Epoch: 1 [52224/58500]	Loss: 0.0942	LR: 0.088646
Training Epoch: 1 [52480/58500]	Loss: 0.0611	LR: 0.089083
Training Epoch: 1 [52736/58500]	Loss: 0.0866	LR: 0.089520
Training Epoch: 1 [52992/58500]	Loss: 0.0502	LR: 0.089956
Training Epoch: 1 [53248/58500]	Loss: 0.0473	LR: 0.090393
Training Epoch: 1 [53504/58500]	Loss: 0.1420	LR: 0.090830
Training Epoch: 1 [53760/58500]	Loss: 0.0853	LR: 0.091266
Training Epoch: 1 [54016/58500]	Loss: 0.0418	LR: 0.091703
Training Epoch: 1 [54272/58500]	Loss: 0.0768	LR: 0.092140
Training Epoch: 1 [54528/58500]	Loss: 0.0759	LR: 0.092576
Training Epoch: 1 [54784/58500]	Loss: 0.0822	LR: 0.093013
Training Epoch: 1 [55040/58500]	Loss: 0.0643	LR: 0.093450
Training Epoch: 1 [55296/58500]	Loss: 0.0693	LR: 0.093886
Training Epoch: 1 [55552/58500]	Loss: 0.0827	LR: 0.094323
Training Epoch: 1 [55808/58500]	Loss: 0.0597	LR: 0.094760
Training Epoch: 1 [56064/58500]	Loss: 0.0865	LR: 0.095197
Training Epoch: 1 [56320/58500]	Loss: 0.1048	LR: 0.095633
Training Epoch: 1 [56576/58500]	Loss: 0.1277	LR: 0.096070
Training Epoch: 1 [56832/58500]	Loss: 0.0481	LR: 0.096507
Training Epoch: 1 [57088/58500]	Loss: 0.0662	LR: 0.096943
Training Epoch: 1 [57344/58500]	Loss: 0.0942	LR: 0.097380
Training Epoch: 1 [57600/58500]	Loss: 0.0847	LR: 0.097817
Training Epoch: 1 [57856/58500]	Loss: 0.1056	LR: 0.098253
Training Epoch: 1 [58112/58500]	Loss: 0.1171	LR: 0.098690
Training Epoch: 1 [58368/58500]	Loss: 0.0477	LR: 0.099127
Training Epoch: 1 [58500/58500]	Loss: 0.0872	LR: 0.099563
Epoch 1 - Average Train Loss: 0.5094, Train Accuracy: 0.8546
Epoch 1 training time consumed: 42.27s
Evaluating Network.....
Test set: Epoch: 1, Average loss: 0.0010, Accuracy: 0.9272, Time consumed:1.76s
Saving weights file to checkpoint/retrain/AllCNN/Wednesday_23_July_2025_07h_08m_27s/AllCNN-Mnist-seed9-ret75-1-best.pth
Training Epoch: 2 [256/58500]	Loss: 0.0658	LR: 0.020000
Training Epoch: 2 [512/58500]	Loss: 0.0565	LR: 0.020000
Training Epoch: 2 [768/58500]	Loss: 0.1049	LR: 0.020000
Training Epoch: 2 [1024/58500]	Loss: 0.0643	LR: 0.020000
Training Epoch: 2 [1280/58500]	Loss: 0.0838	LR: 0.020000
Training Epoch: 2 [1536/58500]	Loss: 0.1015	LR: 0.020000
Training Epoch: 2 [1792/58500]	Loss: 0.0522	LR: 0.020000
Training Epoch: 2 [2048/58500]	Loss: 0.0761	LR: 0.020000
Training Epoch: 2 [2304/58500]	Loss: 0.0433	LR: 0.020000
Training Epoch: 2 [2560/58500]	Loss: 0.0729	LR: 0.020000
Training Epoch: 2 [2816/58500]	Loss: 0.0735	LR: 0.020000
Training Epoch: 2 [3072/58500]	Loss: 0.0529	LR: 0.020000
Training Epoch: 2 [3328/58500]	Loss: 0.0521	LR: 0.020000
Training Epoch: 2 [3584/58500]	Loss: 0.0372	LR: 0.020000
Training Epoch: 2 [3840/58500]	Loss: 0.0579	LR: 0.020000
Training Epoch: 2 [4096/58500]	Loss: 0.0584	LR: 0.020000
Training Epoch: 2 [4352/58500]	Loss: 0.0392	LR: 0.020000
Training Epoch: 2 [4608/58500]	Loss: 0.0502	LR: 0.020000
Training Epoch: 2 [4864/58500]	Loss: 0.0510	LR: 0.020000
Training Epoch: 2 [5120/58500]	Loss: 0.0205	LR: 0.020000
Training Epoch: 2 [5376/58500]	Loss: 0.0775	LR: 0.020000
Training Epoch: 2 [5632/58500]	Loss: 0.0217	LR: 0.020000
Training Epoch: 2 [5888/58500]	Loss: 0.0340	LR: 0.020000
Training Epoch: 2 [6144/58500]	Loss: 0.0312	LR: 0.020000
Training Epoch: 2 [6400/58500]	Loss: 0.0596	LR: 0.020000
Training Epoch: 2 [6656/58500]	Loss: 0.0552	LR: 0.020000
Training Epoch: 2 [6912/58500]	Loss: 0.0343	LR: 0.020000
Training Epoch: 2 [7168/58500]	Loss: 0.0504	LR: 0.020000
Training Epoch: 2 [7424/58500]	Loss: 0.0629	LR: 0.020000
Training Epoch: 2 [7680/58500]	Loss: 0.0900	LR: 0.020000
Training Epoch: 2 [7936/58500]	Loss: 0.0188	LR: 0.020000
Training Epoch: 2 [8192/58500]	Loss: 0.0412	LR: 0.020000
Training Epoch: 2 [8448/58500]	Loss: 0.0513	LR: 0.020000
Training Epoch: 2 [8704/58500]	Loss: 0.0524	LR: 0.020000
Training Epoch: 2 [8960/58500]	Loss: 0.0431	LR: 0.020000
Training Epoch: 2 [9216/58500]	Loss: 0.0647	LR: 0.020000
Training Epoch: 2 [9472/58500]	Loss: 0.0400	LR: 0.020000
Training Epoch: 2 [9728/58500]	Loss: 0.0524	LR: 0.020000
Training Epoch: 2 [9984/58500]	Loss: 0.0532	LR: 0.020000
Training Epoch: 2 [10240/58500]	Loss: 0.0351	LR: 0.020000
Training Epoch: 2 [10496/58500]	Loss: 0.0374	LR: 0.020000
Training Epoch: 2 [10752/58500]	Loss: 0.0334	LR: 0.020000
Training Epoch: 2 [11008/58500]	Loss: 0.0471	LR: 0.020000
Training Epoch: 2 [11264/58500]	Loss: 0.0302	LR: 0.020000
Training Epoch: 2 [11520/58500]	Loss: 0.0237	LR: 0.020000
Training Epoch: 2 [11776/58500]	Loss: 0.0434	LR: 0.020000
Training Epoch: 2 [12032/58500]	Loss: 0.0349	LR: 0.020000
Training Epoch: 2 [12288/58500]	Loss: 0.0290	LR: 0.020000
Training Epoch: 2 [12544/58500]	Loss: 0.0720	LR: 0.020000
Training Epoch: 2 [12800/58500]	Loss: 0.0217	LR: 0.020000
Training Epoch: 2 [13056/58500]	Loss: 0.0676	LR: 0.020000
Training Epoch: 2 [13312/58500]	Loss: 0.0353	LR: 0.020000
Training Epoch: 2 [13568/58500]	Loss: 0.0657	LR: 0.020000
Training Epoch: 2 [13824/58500]	Loss: 0.0264	LR: 0.020000
Training Epoch: 2 [14080/58500]	Loss: 0.0273	LR: 0.020000
Training Epoch: 2 [14336/58500]	Loss: 0.0479	LR: 0.020000
Training Epoch: 2 [14592/58500]	Loss: 0.0776	LR: 0.020000
Training Epoch: 2 [14848/58500]	Loss: 0.0341	LR: 0.020000
Training Epoch: 2 [15104/58500]	Loss: 0.0206	LR: 0.020000
Training Epoch: 2 [15360/58500]	Loss: 0.0266	LR: 0.020000
Training Epoch: 2 [15616/58500]	Loss: 0.0386	LR: 0.020000
Training Epoch: 2 [15872/58500]	Loss: 0.0284	LR: 0.020000
Training Epoch: 2 [16128/58500]	Loss: 0.0387	LR: 0.020000
Training Epoch: 2 [16384/58500]	Loss: 0.0327	LR: 0.020000
Training Epoch: 2 [16640/58500]	Loss: 0.0411	LR: 0.020000
Training Epoch: 2 [16896/58500]	Loss: 0.0473	LR: 0.020000
Training Epoch: 2 [17152/58500]	Loss: 0.0643	LR: 0.020000
Training Epoch: 2 [17408/58500]	Loss: 0.0292	LR: 0.020000
Training Epoch: 2 [17664/58500]	Loss: 0.0385	LR: 0.020000
Training Epoch: 2 [17920/58500]	Loss: 0.0739	LR: 0.020000
Training Epoch: 2 [18176/58500]	Loss: 0.0587	LR: 0.020000
Training Epoch: 2 [18432/58500]	Loss: 0.0266	LR: 0.020000
Training Epoch: 2 [18688/58500]	Loss: 0.0081	LR: 0.020000
Training Epoch: 2 [18944/58500]	Loss: 0.0355	LR: 0.020000
Training Epoch: 2 [19200/58500]	Loss: 0.0401	LR: 0.020000
Training Epoch: 2 [19456/58500]	Loss: 0.0540	LR: 0.020000
Training Epoch: 2 [19712/58500]	Loss: 0.0601	LR: 0.020000
Training Epoch: 2 [19968/58500]	Loss: 0.0316	LR: 0.020000
Training Epoch: 2 [20224/58500]	Loss: 0.0201	LR: 0.020000
Training Epoch: 2 [20480/58500]	Loss: 0.0422	LR: 0.020000
Training Epoch: 2 [20736/58500]	Loss: 0.0396	LR: 0.020000
Training Epoch: 2 [20992/58500]	Loss: 0.0409	LR: 0.020000
Training Epoch: 2 [21248/58500]	Loss: 0.0451	LR: 0.020000
Training Epoch: 2 [21504/58500]	Loss: 0.0475	LR: 0.020000
Training Epoch: 2 [21760/58500]	Loss: 0.0183	LR: 0.020000
Training Epoch: 2 [22016/58500]	Loss: 0.0394	LR: 0.020000
Training Epoch: 2 [22272/58500]	Loss: 0.0210	LR: 0.020000
Training Epoch: 2 [22528/58500]	Loss: 0.0615	LR: 0.020000
Training Epoch: 2 [22784/58500]	Loss: 0.0211	LR: 0.020000
Training Epoch: 2 [23040/58500]	Loss: 0.0300	LR: 0.020000
Training Epoch: 2 [23296/58500]	Loss: 0.0688	LR: 0.020000
Training Epoch: 2 [23552/58500]	Loss: 0.0412	LR: 0.020000
Training Epoch: 2 [23808/58500]	Loss: 0.0478	LR: 0.020000
Training Epoch: 2 [24064/58500]	Loss: 0.0167	LR: 0.020000
Training Epoch: 2 [24320/58500]	Loss: 0.0605	LR: 0.020000
Training Epoch: 2 [24576/58500]	Loss: 0.0357	LR: 0.020000
Training Epoch: 2 [24832/58500]	Loss: 0.0449	LR: 0.020000
Training Epoch: 2 [25088/58500]	Loss: 0.0439	LR: 0.020000
Training Epoch: 2 [25344/58500]	Loss: 0.0135	LR: 0.020000
Training Epoch: 2 [25600/58500]	Loss: 0.0593	LR: 0.020000
Training Epoch: 2 [25856/58500]	Loss: 0.0219	LR: 0.020000
Training Epoch: 2 [26112/58500]	Loss: 0.0334	LR: 0.020000
Training Epoch: 2 [26368/58500]	Loss: 0.0385	LR: 0.020000
Training Epoch: 2 [26624/58500]	Loss: 0.0224	LR: 0.020000
Training Epoch: 2 [26880/58500]	Loss: 0.0192	LR: 0.020000
Training Epoch: 2 [27136/58500]	Loss: 0.0266	LR: 0.020000
Training Epoch: 2 [27392/58500]	Loss: 0.0751	LR: 0.020000
Training Epoch: 2 [27648/58500]	Loss: 0.0450	LR: 0.020000
Training Epoch: 2 [27904/58500]	Loss: 0.0200	LR: 0.020000
Training Epoch: 2 [28160/58500]	Loss: 0.0542	LR: 0.020000
Training Epoch: 2 [28416/58500]	Loss: 0.0327	LR: 0.020000
Training Epoch: 2 [28672/58500]	Loss: 0.0245	LR: 0.020000
Training Epoch: 2 [28928/58500]	Loss: 0.0155	LR: 0.020000
Training Epoch: 2 [29184/58500]	Loss: 0.0288	LR: 0.020000
Training Epoch: 2 [29440/58500]	Loss: 0.0410	LR: 0.020000
Training Epoch: 2 [29696/58500]	Loss: 0.0430	LR: 0.020000
Training Epoch: 2 [29952/58500]	Loss: 0.0620	LR: 0.020000
Training Epoch: 2 [30208/58500]	Loss: 0.0266	LR: 0.020000
Training Epoch: 2 [30464/58500]	Loss: 0.0881	LR: 0.020000
Training Epoch: 2 [30720/58500]	Loss: 0.0544	LR: 0.020000
Training Epoch: 2 [30976/58500]	Loss: 0.0331	LR: 0.020000
Training Epoch: 2 [31232/58500]	Loss: 0.0632	LR: 0.020000
Training Epoch: 2 [31488/58500]	Loss: 0.0348	LR: 0.020000
Training Epoch: 2 [31744/58500]	Loss: 0.0286	LR: 0.020000
Training Epoch: 2 [32000/58500]	Loss: 0.0497	LR: 0.020000
Training Epoch: 2 [32256/58500]	Loss: 0.0297	LR: 0.020000
Training Epoch: 2 [32512/58500]	Loss: 0.0117	LR: 0.020000
Training Epoch: 2 [32768/58500]	Loss: 0.0103	LR: 0.020000
Training Epoch: 2 [33024/58500]	Loss: 0.0437	LR: 0.020000
Training Epoch: 2 [33280/58500]	Loss: 0.0585	LR: 0.020000
Training Epoch: 2 [33536/58500]	Loss: 0.0339	LR: 0.020000
Training Epoch: 2 [33792/58500]	Loss: 0.0225	LR: 0.020000
Training Epoch: 2 [34048/58500]	Loss: 0.0294	LR: 0.020000
Training Epoch: 2 [34304/58500]	Loss: 0.0293	LR: 0.020000
Training Epoch: 2 [34560/58500]	Loss: 0.0294	LR: 0.020000
Training Epoch: 2 [34816/58500]	Loss: 0.0282	LR: 0.020000
Training Epoch: 2 [35072/58500]	Loss: 0.0474	LR: 0.020000
Training Epoch: 2 [35328/58500]	Loss: 0.0510	LR: 0.020000
Training Epoch: 2 [35584/58500]	Loss: 0.0685	LR: 0.020000
Training Epoch: 2 [35840/58500]	Loss: 0.0611	LR: 0.020000
Training Epoch: 2 [36096/58500]	Loss: 0.0196	LR: 0.020000
Training Epoch: 2 [36352/58500]	Loss: 0.0259	LR: 0.020000
Training Epoch: 2 [36608/58500]	Loss: 0.0149	LR: 0.020000
Training Epoch: 2 [36864/58500]	Loss: 0.0500	LR: 0.020000
Training Epoch: 2 [37120/58500]	Loss: 0.0250	LR: 0.020000
Training Epoch: 2 [37376/58500]	Loss: 0.0349	LR: 0.020000
Training Epoch: 2 [37632/58500]	Loss: 0.0212	LR: 0.020000
Training Epoch: 2 [37888/58500]	Loss: 0.0264	LR: 0.020000
Training Epoch: 2 [38144/58500]	Loss: 0.0223	LR: 0.020000
Training Epoch: 2 [38400/58500]	Loss: 0.0449	LR: 0.020000
Training Epoch: 2 [38656/58500]	Loss: 0.0301	LR: 0.020000
Training Epoch: 2 [38912/58500]	Loss: 0.0216	LR: 0.020000
Training Epoch: 2 [39168/58500]	Loss: 0.0133	LR: 0.020000
Training Epoch: 2 [39424/58500]	Loss: 0.0424	LR: 0.020000
Training Epoch: 2 [39680/58500]	Loss: 0.0345	LR: 0.020000
Training Epoch: 2 [39936/58500]	Loss: 0.0487	LR: 0.020000
Training Epoch: 2 [40192/58500]	Loss: 0.0259	LR: 0.020000
Training Epoch: 2 [40448/58500]	Loss: 0.0493	LR: 0.020000
Training Epoch: 2 [40704/58500]	Loss: 0.0270	LR: 0.020000
Training Epoch: 2 [40960/58500]	Loss: 0.0428	LR: 0.020000
Training Epoch: 2 [41216/58500]	Loss: 0.0229	LR: 0.020000
Training Epoch: 2 [41472/58500]	Loss: 0.0143	LR: 0.020000
Training Epoch: 2 [41728/58500]	Loss: 0.0267	LR: 0.020000
Training Epoch: 2 [41984/58500]	Loss: 0.0535	LR: 0.020000
Training Epoch: 2 [42240/58500]	Loss: 0.0532	LR: 0.020000
Training Epoch: 2 [42496/58500]	Loss: 0.0628	LR: 0.020000
Training Epoch: 2 [42752/58500]	Loss: 0.0272	LR: 0.020000
Training Epoch: 2 [43008/58500]	Loss: 0.0545	LR: 0.020000
Training Epoch: 2 [43264/58500]	Loss: 0.0267	LR: 0.020000
Training Epoch: 2 [43520/58500]	Loss: 0.0475	LR: 0.020000
Training Epoch: 2 [43776/58500]	Loss: 0.0468	LR: 0.020000
Training Epoch: 2 [44032/58500]	Loss: 0.0118	LR: 0.020000
Training Epoch: 2 [44288/58500]	Loss: 0.0313	LR: 0.020000
Training Epoch: 2 [44544/58500]	Loss: 0.0282	LR: 0.020000
Training Epoch: 2 [44800/58500]	Loss: 0.0329	LR: 0.020000
Training Epoch: 2 [45056/58500]	Loss: 0.0322	LR: 0.020000
Training Epoch: 2 [45312/58500]	Loss: 0.0367	LR: 0.020000
Training Epoch: 2 [45568/58500]	Loss: 0.0580	LR: 0.020000
Training Epoch: 2 [45824/58500]	Loss: 0.0372	LR: 0.020000
Training Epoch: 2 [46080/58500]	Loss: 0.0277	LR: 0.020000
Training Epoch: 2 [46336/58500]	Loss: 0.0600	LR: 0.020000
Training Epoch: 2 [46592/58500]	Loss: 0.0285	LR: 0.020000
Training Epoch: 2 [46848/58500]	Loss: 0.0590	LR: 0.020000
Training Epoch: 2 [47104/58500]	Loss: 0.0290	LR: 0.020000
Training Epoch: 2 [47360/58500]	Loss: 0.0337	LR: 0.020000
Training Epoch: 2 [47616/58500]	Loss: 0.0448	LR: 0.020000
Training Epoch: 2 [47872/58500]	Loss: 0.0089	LR: 0.020000
Training Epoch: 2 [48128/58500]	Loss: 0.0388	LR: 0.020000
Training Epoch: 2 [48384/58500]	Loss: 0.0325	LR: 0.020000
Training Epoch: 2 [48640/58500]	Loss: 0.0367	LR: 0.020000
Training Epoch: 2 [48896/58500]	Loss: 0.0229	LR: 0.020000
Training Epoch: 2 [49152/58500]	Loss: 0.0386	LR: 0.020000
Training Epoch: 2 [49408/58500]	Loss: 0.0354	LR: 0.020000
Training Epoch: 2 [49664/58500]	Loss: 0.0170	LR: 0.020000
Training Epoch: 2 [49920/58500]	Loss: 0.0159	LR: 0.020000
Training Epoch: 2 [50176/58500]	Loss: 0.0382	LR: 0.020000
Training Epoch: 2 [50432/58500]	Loss: 0.0432	LR: 0.020000
Training Epoch: 2 [50688/58500]	Loss: 0.0210	LR: 0.020000
Training Epoch: 2 [50944/58500]	Loss: 0.0346	LR: 0.020000
Training Epoch: 2 [51200/58500]	Loss: 0.0362	LR: 0.020000
Training Epoch: 2 [51456/58500]	Loss: 0.0330	LR: 0.020000
Training Epoch: 2 [51712/58500]	Loss: 0.0807	LR: 0.020000
Training Epoch: 2 [51968/58500]	Loss: 0.0459	LR: 0.020000
Training Epoch: 2 [52224/58500]	Loss: 0.0251	LR: 0.020000
Training Epoch: 2 [52480/58500]	Loss: 0.0363	LR: 0.020000
Training Epoch: 2 [52736/58500]	Loss: 0.0306	LR: 0.020000
Training Epoch: 2 [52992/58500]	Loss: 0.0274	LR: 0.020000
Training Epoch: 2 [53248/58500]	Loss: 0.0133	LR: 0.020000
Training Epoch: 2 [53504/58500]	Loss: 0.0428	LR: 0.020000
Training Epoch: 2 [53760/58500]	Loss: 0.0481	LR: 0.020000
Training Epoch: 2 [54016/58500]	Loss: 0.0260	LR: 0.020000
Training Epoch: 2 [54272/58500]	Loss: 0.0544	LR: 0.020000
Training Epoch: 2 [54528/58500]	Loss: 0.0663	LR: 0.020000
Training Epoch: 2 [54784/58500]	Loss: 0.0137	LR: 0.020000
Training Epoch: 2 [55040/58500]	Loss: 0.0419	LR: 0.020000
Training Epoch: 2 [55296/58500]	Loss: 0.0382	LR: 0.020000
Training Epoch: 2 [55552/58500]	Loss: 0.0424	LR: 0.020000
Training Epoch: 2 [55808/58500]	Loss: 0.0209	LR: 0.020000
Training Epoch: 2 [56064/58500]	Loss: 0.0268	LR: 0.020000
Training Epoch: 2 [56320/58500]	Loss: 0.0210	LR: 0.020000
Training Epoch: 2 [56576/58500]	Loss: 0.0276	LR: 0.020000
Training Epoch: 2 [56832/58500]	Loss: 0.0307	LR: 0.020000
Training Epoch: 2 [57088/58500]	Loss: 0.0294	LR: 0.020000
Training Epoch: 2 [57344/58500]	Loss: 0.0462	LR: 0.020000
Training Epoch: 2 [57600/58500]	Loss: 0.0387	LR: 0.020000
Training Epoch: 2 [57856/58500]	Loss: 0.0268	LR: 0.020000
Training Epoch: 2 [58112/58500]	Loss: 0.0179	LR: 0.020000
Training Epoch: 2 [58368/58500]	Loss: 0.0487	LR: 0.020000
Training Epoch: 2 [58500/58500]	Loss: 0.0865	LR: 0.020000
Epoch 2 - Average Train Loss: 0.0403, Train Accuracy: 0.9884
Epoch 2 training time consumed: 41.82s
Evaluating Network.....
Test set: Epoch: 2, Average loss: 0.0001, Accuracy: 0.9946, Time consumed:1.72s
Saving weights file to checkpoint/retrain/AllCNN/Wednesday_23_July_2025_07h_08m_27s/AllCNN-Mnist-seed9-ret75-2-best.pth
Training Epoch: 3 [256/58500]	Loss: 0.0295	LR: 0.004000
Training Epoch: 3 [512/58500]	Loss: 0.0272	LR: 0.004000
Training Epoch: 3 [768/58500]	Loss: 0.0178	LR: 0.004000
Training Epoch: 3 [1024/58500]	Loss: 0.0207	LR: 0.004000
Training Epoch: 3 [1280/58500]	Loss: 0.0333	LR: 0.004000
Training Epoch: 3 [1536/58500]	Loss: 0.0368	LR: 0.004000
Training Epoch: 3 [1792/58500]	Loss: 0.0201	LR: 0.004000
Training Epoch: 3 [2048/58500]	Loss: 0.0284	LR: 0.004000
Training Epoch: 3 [2304/58500]	Loss: 0.0266	LR: 0.004000
Training Epoch: 3 [2560/58500]	Loss: 0.0427	LR: 0.004000
Training Epoch: 3 [2816/58500]	Loss: 0.0245	LR: 0.004000
Training Epoch: 3 [3072/58500]	Loss: 0.0297	LR: 0.004000
Training Epoch: 3 [3328/58500]	Loss: 0.0180	LR: 0.004000
Training Epoch: 3 [3584/58500]	Loss: 0.0231	LR: 0.004000
Training Epoch: 3 [3840/58500]	Loss: 0.0163	LR: 0.004000
Training Epoch: 3 [4096/58500]	Loss: 0.0267	LR: 0.004000
Training Epoch: 3 [4352/58500]	Loss: 0.0330	LR: 0.004000
Training Epoch: 3 [4608/58500]	Loss: 0.0110	LR: 0.004000
Training Epoch: 3 [4864/58500]	Loss: 0.0529	LR: 0.004000
Training Epoch: 3 [5120/58500]	Loss: 0.0353	LR: 0.004000
Training Epoch: 3 [5376/58500]	Loss: 0.0279	LR: 0.004000
Training Epoch: 3 [5632/58500]	Loss: 0.0398	LR: 0.004000
Training Epoch: 3 [5888/58500]	Loss: 0.0212	LR: 0.004000
Training Epoch: 3 [6144/58500]	Loss: 0.0272	LR: 0.004000
Training Epoch: 3 [6400/58500]	Loss: 0.0168	LR: 0.004000
Training Epoch: 3 [6656/58500]	Loss: 0.0200	LR: 0.004000
Training Epoch: 3 [6912/58500]	Loss: 0.0260	LR: 0.004000
Training Epoch: 3 [7168/58500]	Loss: 0.0220	LR: 0.004000
Training Epoch: 3 [7424/58500]	Loss: 0.0229	LR: 0.004000
Training Epoch: 3 [7680/58500]	Loss: 0.0290	LR: 0.004000
Training Epoch: 3 [7936/58500]	Loss: 0.0287	LR: 0.004000
Training Epoch: 3 [8192/58500]	Loss: 0.0230	LR: 0.004000
Training Epoch: 3 [8448/58500]	Loss: 0.0256	LR: 0.004000
Training Epoch: 3 [8704/58500]	Loss: 0.0274	LR: 0.004000
Training Epoch: 3 [8960/58500]	Loss: 0.0318	LR: 0.004000
Training Epoch: 3 [9216/58500]	Loss: 0.0182	LR: 0.004000
Training Epoch: 3 [9472/58500]	Loss: 0.0289	LR: 0.004000
Training Epoch: 3 [9728/58500]	Loss: 0.0348	LR: 0.004000
Training Epoch: 3 [9984/58500]	Loss: 0.0233	LR: 0.004000
Training Epoch: 3 [10240/58500]	Loss: 0.0329	LR: 0.004000
Training Epoch: 3 [10496/58500]	Loss: 0.0521	LR: 0.004000
Training Epoch: 3 [10752/58500]	Loss: 0.0217	LR: 0.004000
Training Epoch: 3 [11008/58500]	Loss: 0.0390	LR: 0.004000
Training Epoch: 3 [11264/58500]	Loss: 0.0225	LR: 0.004000
Training Epoch: 3 [11520/58500]	Loss: 0.0090	LR: 0.004000
Training Epoch: 3 [11776/58500]	Loss: 0.0339	LR: 0.004000
Training Epoch: 3 [12032/58500]	Loss: 0.0203	LR: 0.004000
Training Epoch: 3 [12288/58500]	Loss: 0.0141	LR: 0.004000
Training Epoch: 3 [12544/58500]	Loss: 0.0285	LR: 0.004000
Training Epoch: 3 [12800/58500]	Loss: 0.0274	LR: 0.004000
Training Epoch: 3 [13056/58500]	Loss: 0.0301	LR: 0.004000
Training Epoch: 3 [13312/58500]	Loss: 0.0480	LR: 0.004000
Training Epoch: 3 [13568/58500]	Loss: 0.0286	LR: 0.004000
Training Epoch: 3 [13824/58500]	Loss: 0.0333	LR: 0.004000
Training Epoch: 3 [14080/58500]	Loss: 0.0331	LR: 0.004000
Training Epoch: 3 [14336/58500]	Loss: 0.0255	LR: 0.004000
Training Epoch: 3 [14592/58500]	Loss: 0.0319	LR: 0.004000
Training Epoch: 3 [14848/58500]	Loss: 0.0228	LR: 0.004000
Training Epoch: 3 [15104/58500]	Loss: 0.0225	LR: 0.004000
Training Epoch: 3 [15360/58500]	Loss: 0.0590	LR: 0.004000
Training Epoch: 3 [15616/58500]	Loss: 0.0104	LR: 0.004000
Training Epoch: 3 [15872/58500]	Loss: 0.0192	LR: 0.004000
Training Epoch: 3 [16128/58500]	Loss: 0.0437	LR: 0.004000
Training Epoch: 3 [16384/58500]	Loss: 0.0306	LR: 0.004000
Training Epoch: 3 [16640/58500]	Loss: 0.0333	LR: 0.004000
Training Epoch: 3 [16896/58500]	Loss: 0.0325	LR: 0.004000
Training Epoch: 3 [17152/58500]	Loss: 0.0246	LR: 0.004000
Training Epoch: 3 [17408/58500]	Loss: 0.0263	LR: 0.004000
Training Epoch: 3 [17664/58500]	Loss: 0.0228	LR: 0.004000
Training Epoch: 3 [17920/58500]	Loss: 0.0471	LR: 0.004000
Training Epoch: 3 [18176/58500]	Loss: 0.0243	LR: 0.004000
Training Epoch: 3 [18432/58500]	Loss: 0.0334	LR: 0.004000
Training Epoch: 3 [18688/58500]	Loss: 0.0186	LR: 0.004000
Training Epoch: 3 [18944/58500]	Loss: 0.0813	LR: 0.004000
Training Epoch: 3 [19200/58500]	Loss: 0.0315	LR: 0.004000
Training Epoch: 3 [19456/58500]	Loss: 0.0211	LR: 0.004000
Training Epoch: 3 [19712/58500]	Loss: 0.0489	LR: 0.004000
Training Epoch: 3 [19968/58500]	Loss: 0.0151	LR: 0.004000
Training Epoch: 3 [20224/58500]	Loss: 0.0130	LR: 0.004000
Training Epoch: 3 [20480/58500]	Loss: 0.0258	LR: 0.004000
Training Epoch: 3 [20736/58500]	Loss: 0.0163	LR: 0.004000
Training Epoch: 3 [20992/58500]	Loss: 0.0152	LR: 0.004000
Training Epoch: 3 [21248/58500]	Loss: 0.0228	LR: 0.004000
Training Epoch: 3 [21504/58500]	Loss: 0.0424	LR: 0.004000
Training Epoch: 3 [21760/58500]	Loss: 0.0216	LR: 0.004000
Training Epoch: 3 [22016/58500]	Loss: 0.0268	LR: 0.004000
Training Epoch: 3 [22272/58500]	Loss: 0.0374	LR: 0.004000
Training Epoch: 3 [22528/58500]	Loss: 0.0454	LR: 0.004000
Training Epoch: 3 [22784/58500]	Loss: 0.0228	LR: 0.004000
Training Epoch: 3 [23040/58500]	Loss: 0.0247	LR: 0.004000
Training Epoch: 3 [23296/58500]	Loss: 0.0198	LR: 0.004000
Training Epoch: 3 [23552/58500]	Loss: 0.0340	LR: 0.004000
Training Epoch: 3 [23808/58500]	Loss: 0.0217	LR: 0.004000
Training Epoch: 3 [24064/58500]	Loss: 0.0420	LR: 0.004000
Training Epoch: 3 [24320/58500]	Loss: 0.0214	LR: 0.004000
Training Epoch: 3 [24576/58500]	Loss: 0.0249	LR: 0.004000
Training Epoch: 3 [24832/58500]	Loss: 0.0627	LR: 0.004000
Training Epoch: 3 [25088/58500]	Loss: 0.0174	LR: 0.004000
Training Epoch: 3 [25344/58500]	Loss: 0.0192	LR: 0.004000
Training Epoch: 3 [25600/58500]	Loss: 0.0143	LR: 0.004000
Training Epoch: 3 [25856/58500]	Loss: 0.0125	LR: 0.004000
Training Epoch: 3 [26112/58500]	Loss: 0.0196	LR: 0.004000
Training Epoch: 3 [26368/58500]	Loss: 0.0198	LR: 0.004000
Training Epoch: 3 [26624/58500]	Loss: 0.0190	LR: 0.004000
Training Epoch: 3 [26880/58500]	Loss: 0.0134	LR: 0.004000
Training Epoch: 3 [27136/58500]	Loss: 0.0092	LR: 0.004000
Training Epoch: 3 [27392/58500]	Loss: 0.0287	LR: 0.004000
Training Epoch: 3 [27648/58500]	Loss: 0.0119	LR: 0.004000
Training Epoch: 3 [27904/58500]	Loss: 0.0391	LR: 0.004000
Training Epoch: 3 [28160/58500]	Loss: 0.0250	LR: 0.004000
Training Epoch: 3 [28416/58500]	Loss: 0.0407	LR: 0.004000
Training Epoch: 3 [28672/58500]	Loss: 0.0280	LR: 0.004000
Training Epoch: 3 [28928/58500]	Loss: 0.0088	LR: 0.004000
Training Epoch: 3 [29184/58500]	Loss: 0.0273	LR: 0.004000
Training Epoch: 3 [29440/58500]	Loss: 0.0219	LR: 0.004000
Training Epoch: 3 [29696/58500]	Loss: 0.0275	LR: 0.004000
Training Epoch: 3 [29952/58500]	Loss: 0.0152	LR: 0.004000
Training Epoch: 3 [30208/58500]	Loss: 0.0255	LR: 0.004000
Training Epoch: 3 [30464/58500]	Loss: 0.0263	LR: 0.004000
Training Epoch: 3 [30720/58500]	Loss: 0.0126	LR: 0.004000
Training Epoch: 3 [30976/58500]	Loss: 0.0191	LR: 0.004000
Training Epoch: 3 [31232/58500]	Loss: 0.0289	LR: 0.004000
Training Epoch: 3 [31488/58500]	Loss: 0.0386	LR: 0.004000
Training Epoch: 3 [31744/58500]	Loss: 0.0208	LR: 0.004000
Training Epoch: 3 [32000/58500]	Loss: 0.0128	LR: 0.004000
Training Epoch: 3 [32256/58500]	Loss: 0.0289	LR: 0.004000
Training Epoch: 3 [32512/58500]	Loss: 0.0175	LR: 0.004000
Training Epoch: 3 [32768/58500]	Loss: 0.0333	LR: 0.004000
Training Epoch: 3 [33024/58500]	Loss: 0.0140	LR: 0.004000
Training Epoch: 3 [33280/58500]	Loss: 0.0182	LR: 0.004000
Training Epoch: 3 [33536/58500]	Loss: 0.0202	LR: 0.004000
Training Epoch: 3 [33792/58500]	Loss: 0.0269	LR: 0.004000
Training Epoch: 3 [34048/58500]	Loss: 0.0479	LR: 0.004000
Training Epoch: 3 [34304/58500]	Loss: 0.0374	LR: 0.004000
Training Epoch: 3 [34560/58500]	Loss: 0.0239	LR: 0.004000
Training Epoch: 3 [34816/58500]	Loss: 0.0327	LR: 0.004000
Training Epoch: 3 [35072/58500]	Loss: 0.0270	LR: 0.004000
Training Epoch: 3 [35328/58500]	Loss: 0.0139	LR: 0.004000
Training Epoch: 3 [35584/58500]	Loss: 0.0133	LR: 0.004000
Training Epoch: 3 [35840/58500]	Loss: 0.0255	LR: 0.004000
Training Epoch: 3 [36096/58500]	Loss: 0.0486	LR: 0.004000
Training Epoch: 3 [36352/58500]	Loss: 0.0631	LR: 0.004000
Training Epoch: 3 [36608/58500]	Loss: 0.0363	LR: 0.004000
Training Epoch: 3 [36864/58500]	Loss: 0.0169	LR: 0.004000
Training Epoch: 3 [37120/58500]	Loss: 0.0160	LR: 0.004000
Training Epoch: 3 [37376/58500]	Loss: 0.0300	LR: 0.004000
Training Epoch: 3 [37632/58500]	Loss: 0.0384	LR: 0.004000
Training Epoch: 3 [37888/58500]	Loss: 0.0137	LR: 0.004000
Training Epoch: 3 [38144/58500]	Loss: 0.0470	LR: 0.004000
Training Epoch: 3 [38400/58500]	Loss: 0.0236	LR: 0.004000
Training Epoch: 3 [38656/58500]	Loss: 0.0375	LR: 0.004000
Training Epoch: 3 [38912/58500]	Loss: 0.0064	LR: 0.004000
Training Epoch: 3 [39168/58500]	Loss: 0.0437	LR: 0.004000
Training Epoch: 3 [39424/58500]	Loss: 0.0312	LR: 0.004000
Training Epoch: 3 [39680/58500]	Loss: 0.0292	LR: 0.004000
Training Epoch: 3 [39936/58500]	Loss: 0.0284	LR: 0.004000
Training Epoch: 3 [40192/58500]	Loss: 0.0297	LR: 0.004000
Training Epoch: 3 [40448/58500]	Loss: 0.0224	LR: 0.004000
Training Epoch: 3 [40704/58500]	Loss: 0.0075	LR: 0.004000
Training Epoch: 3 [40960/58500]	Loss: 0.0160	LR: 0.004000
Training Epoch: 3 [41216/58500]	Loss: 0.0258	LR: 0.004000
Training Epoch: 3 [41472/58500]	Loss: 0.0197	LR: 0.004000
Training Epoch: 3 [41728/58500]	Loss: 0.0137	LR: 0.004000
Training Epoch: 3 [41984/58500]	Loss: 0.0395	LR: 0.004000
Training Epoch: 3 [42240/58500]	Loss: 0.0127	LR: 0.004000
Training Epoch: 3 [42496/58500]	Loss: 0.0132	LR: 0.004000
Training Epoch: 3 [42752/58500]	Loss: 0.0189	LR: 0.004000
Training Epoch: 3 [43008/58500]	Loss: 0.0265	LR: 0.004000
Training Epoch: 3 [43264/58500]	Loss: 0.0413	LR: 0.004000
Training Epoch: 3 [43520/58500]	Loss: 0.0306	LR: 0.004000
Training Epoch: 3 [43776/58500]	Loss: 0.0190	LR: 0.004000
Training Epoch: 3 [44032/58500]	Loss: 0.0395	LR: 0.004000
Training Epoch: 3 [44288/58500]	Loss: 0.0153	LR: 0.004000
Training Epoch: 3 [44544/58500]	Loss: 0.0355	LR: 0.004000
Training Epoch: 3 [44800/58500]	Loss: 0.0199	LR: 0.004000
Training Epoch: 3 [45056/58500]	Loss: 0.0425	LR: 0.004000
Training Epoch: 3 [45312/58500]	Loss: 0.0507	LR: 0.004000
Training Epoch: 3 [45568/58500]	Loss: 0.0429	LR: 0.004000
Training Epoch: 3 [45824/58500]	Loss: 0.0242	LR: 0.004000
Training Epoch: 3 [46080/58500]	Loss: 0.0134	LR: 0.004000
Training Epoch: 3 [46336/58500]	Loss: 0.0361	LR: 0.004000
Training Epoch: 3 [46592/58500]	Loss: 0.0217	LR: 0.004000
Training Epoch: 3 [46848/58500]	Loss: 0.0133	LR: 0.004000
Training Epoch: 3 [47104/58500]	Loss: 0.0116	LR: 0.004000
Training Epoch: 3 [47360/58500]	Loss: 0.0239	LR: 0.004000
Training Epoch: 3 [47616/58500]	Loss: 0.0159	LR: 0.004000
Training Epoch: 3 [47872/58500]	Loss: 0.0134	LR: 0.004000
Training Epoch: 3 [48128/58500]	Loss: 0.0263	LR: 0.004000
Training Epoch: 3 [48384/58500]	Loss: 0.0103	LR: 0.004000
Training Epoch: 3 [48640/58500]	Loss: 0.0360	LR: 0.004000
Training Epoch: 3 [48896/58500]	Loss: 0.0131	LR: 0.004000
Training Epoch: 3 [49152/58500]	Loss: 0.0201	LR: 0.004000
Training Epoch: 3 [49408/58500]	Loss: 0.0219	LR: 0.004000
Training Epoch: 3 [49664/58500]	Loss: 0.0189	LR: 0.004000
Training Epoch: 3 [49920/58500]	Loss: 0.0443	LR: 0.004000
Training Epoch: 3 [50176/58500]	Loss: 0.0284	LR: 0.004000
Training Epoch: 3 [50432/58500]	Loss: 0.0282	LR: 0.004000
Training Epoch: 3 [50688/58500]	Loss: 0.0179	LR: 0.004000
Training Epoch: 3 [50944/58500]	Loss: 0.0179	LR: 0.004000
Training Epoch: 3 [51200/58500]	Loss: 0.0212	LR: 0.004000
Training Epoch: 3 [51456/58500]	Loss: 0.0262	LR: 0.004000
Training Epoch: 3 [51712/58500]	Loss: 0.0254	LR: 0.004000
Training Epoch: 3 [51968/58500]	Loss: 0.0177	LR: 0.004000
Training Epoch: 3 [52224/58500]	Loss: 0.0295	LR: 0.004000
Training Epoch: 3 [52480/58500]	Loss: 0.0294	LR: 0.004000
Training Epoch: 3 [52736/58500]	Loss: 0.0250	LR: 0.004000
Training Epoch: 3 [52992/58500]	Loss: 0.0552	LR: 0.004000
Training Epoch: 3 [53248/58500]	Loss: 0.0147	LR: 0.004000
Training Epoch: 3 [53504/58500]	Loss: 0.0343	LR: 0.004000
Training Epoch: 3 [53760/58500]	Loss: 0.0135	LR: 0.004000
Training Epoch: 3 [54016/58500]	Loss: 0.0151	LR: 0.004000
Training Epoch: 3 [54272/58500]	Loss: 0.0315	LR: 0.004000
Training Epoch: 3 [54528/58500]	Loss: 0.0198	LR: 0.004000
Training Epoch: 3 [54784/58500]	Loss: 0.0076	LR: 0.004000
Training Epoch: 3 [55040/58500]	Loss: 0.0215	LR: 0.004000
Training Epoch: 3 [55296/58500]	Loss: 0.0221	LR: 0.004000
Training Epoch: 3 [55552/58500]	Loss: 0.0171	LR: 0.004000
Training Epoch: 3 [55808/58500]	Loss: 0.0169	LR: 0.004000
Training Epoch: 3 [56064/58500]	Loss: 0.0185	LR: 0.004000
Training Epoch: 3 [56320/58500]	Loss: 0.0065	LR: 0.004000
Training Epoch: 3 [56576/58500]	Loss: 0.0224	LR: 0.004000
Training Epoch: 3 [56832/58500]	Loss: 0.0117	LR: 0.004000
Training Epoch: 3 [57088/58500]	Loss: 0.0638	LR: 0.004000
Training Epoch: 3 [57344/58500]	Loss: 0.0075	LR: 0.004000
Training Epoch: 3 [57600/58500]	Loss: 0.0371	LR: 0.004000
Training Epoch: 3 [57856/58500]	Loss: 0.0290	LR: 0.004000
Training Epoch: 3 [58112/58500]	Loss: 0.0118	LR: 0.004000
Training Epoch: 3 [58368/58500]	Loss: 0.0305	LR: 0.004000
Training Epoch: 3 [58500/58500]	Loss: 0.0340	LR: 0.004000
Epoch 3 - Average Train Loss: 0.0264, Train Accuracy: 0.9925
Epoch 3 training time consumed: 41.66s
Evaluating Network.....
Test set: Epoch: 3, Average loss: 0.0001, Accuracy: 0.9950, Time consumed:1.71s
Saving weights file to checkpoint/retrain/AllCNN/Wednesday_23_July_2025_07h_08m_27s/AllCNN-Mnist-seed9-ret75-3-best.pth
Training Epoch: 4 [256/58500]	Loss: 0.0165	LR: 0.000800
Training Epoch: 4 [512/58500]	Loss: 0.0206	LR: 0.000800
Training Epoch: 4 [768/58500]	Loss: 0.0365	LR: 0.000800
Training Epoch: 4 [1024/58500]	Loss: 0.0189	LR: 0.000800
Training Epoch: 4 [1280/58500]	Loss: 0.0148	LR: 0.000800
Training Epoch: 4 [1536/58500]	Loss: 0.0206	LR: 0.000800
Training Epoch: 4 [1792/58500]	Loss: 0.0232	LR: 0.000800
Training Epoch: 4 [2048/58500]	Loss: 0.0226	LR: 0.000800
Training Epoch: 4 [2304/58500]	Loss: 0.0320	LR: 0.000800
Training Epoch: 4 [2560/58500]	Loss: 0.0172	LR: 0.000800
Training Epoch: 4 [2816/58500]	Loss: 0.0269	LR: 0.000800
Training Epoch: 4 [3072/58500]	Loss: 0.0225	LR: 0.000800
Training Epoch: 4 [3328/58500]	Loss: 0.0101	LR: 0.000800
Training Epoch: 4 [3584/58500]	Loss: 0.0246	LR: 0.000800
Training Epoch: 4 [3840/58500]	Loss: 0.0208	LR: 0.000800
Training Epoch: 4 [4096/58500]	Loss: 0.0283	LR: 0.000800
Training Epoch: 4 [4352/58500]	Loss: 0.0187	LR: 0.000800
Training Epoch: 4 [4608/58500]	Loss: 0.0258	LR: 0.000800
Training Epoch: 4 [4864/58500]	Loss: 0.0224	LR: 0.000800
Training Epoch: 4 [5120/58500]	Loss: 0.0153	LR: 0.000800
Training Epoch: 4 [5376/58500]	Loss: 0.0432	LR: 0.000800
Training Epoch: 4 [5632/58500]	Loss: 0.0086	LR: 0.000800
Training Epoch: 4 [5888/58500]	Loss: 0.0417	LR: 0.000800
Training Epoch: 4 [6144/58500]	Loss: 0.0260	LR: 0.000800
Training Epoch: 4 [6400/58500]	Loss: 0.0093	LR: 0.000800
Training Epoch: 4 [6656/58500]	Loss: 0.0236	LR: 0.000800
Training Epoch: 4 [6912/58500]	Loss: 0.0372	LR: 0.000800
Training Epoch: 4 [7168/58500]	Loss: 0.0393	LR: 0.000800
Training Epoch: 4 [7424/58500]	Loss: 0.0316	LR: 0.000800
Training Epoch: 4 [7680/58500]	Loss: 0.0510	LR: 0.000800
Training Epoch: 4 [7936/58500]	Loss: 0.0291	LR: 0.000800
Training Epoch: 4 [8192/58500]	Loss: 0.0145	LR: 0.000800
Training Epoch: 4 [8448/58500]	Loss: 0.0188	LR: 0.000800
Training Epoch: 4 [8704/58500]	Loss: 0.0323	LR: 0.000800
Training Epoch: 4 [8960/58500]	Loss: 0.0317	LR: 0.000800
Training Epoch: 4 [9216/58500]	Loss: 0.0182	LR: 0.000800
Training Epoch: 4 [9472/58500]	Loss: 0.0237	LR: 0.000800
Training Epoch: 4 [9728/58500]	Loss: 0.0181	LR: 0.000800
Training Epoch: 4 [9984/58500]	Loss: 0.0356	LR: 0.000800
Training Epoch: 4 [10240/58500]	Loss: 0.0129	LR: 0.000800
Training Epoch: 4 [10496/58500]	Loss: 0.0484	LR: 0.000800
Training Epoch: 4 [10752/58500]	Loss: 0.0321	LR: 0.000800
Training Epoch: 4 [11008/58500]	Loss: 0.0089	LR: 0.000800
Training Epoch: 4 [11264/58500]	Loss: 0.0482	LR: 0.000800
Training Epoch: 4 [11520/58500]	Loss: 0.0397	LR: 0.000800
Training Epoch: 4 [11776/58500]	Loss: 0.0096	LR: 0.000800
Training Epoch: 4 [12032/58500]	Loss: 0.0119	LR: 0.000800
Training Epoch: 4 [12288/58500]	Loss: 0.0417	LR: 0.000800
Training Epoch: 4 [12544/58500]	Loss: 0.0096	LR: 0.000800
Training Epoch: 4 [12800/58500]	Loss: 0.0374	LR: 0.000800
Training Epoch: 4 [13056/58500]	Loss: 0.0142	LR: 0.000800
Training Epoch: 4 [13312/58500]	Loss: 0.0233	LR: 0.000800
Training Epoch: 4 [13568/58500]	Loss: 0.0181	LR: 0.000800
Training Epoch: 4 [13824/58500]	Loss: 0.0208	LR: 0.000800
Training Epoch: 4 [14080/58500]	Loss: 0.0209	LR: 0.000800
Training Epoch: 4 [14336/58500]	Loss: 0.0534	LR: 0.000800
Training Epoch: 4 [14592/58500]	Loss: 0.0215	LR: 0.000800
Training Epoch: 4 [14848/58500]	Loss: 0.0214	LR: 0.000800
Training Epoch: 4 [15104/58500]	Loss: 0.0181	LR: 0.000800
Training Epoch: 4 [15360/58500]	Loss: 0.0171	LR: 0.000800
Training Epoch: 4 [15616/58500]	Loss: 0.0258	LR: 0.000800
Training Epoch: 4 [15872/58500]	Loss: 0.0318	LR: 0.000800
Training Epoch: 4 [16128/58500]	Loss: 0.0373	LR: 0.000800
Training Epoch: 4 [16384/58500]	Loss: 0.0171	LR: 0.000800
Training Epoch: 4 [16640/58500]	Loss: 0.0236	LR: 0.000800
Training Epoch: 4 [16896/58500]	Loss: 0.0510	LR: 0.000800
Training Epoch: 4 [17152/58500]	Loss: 0.0402	LR: 0.000800
Training Epoch: 4 [17408/58500]	Loss: 0.0127	LR: 0.000800
Training Epoch: 4 [17664/58500]	Loss: 0.0100	LR: 0.000800
Training Epoch: 4 [17920/58500]	Loss: 0.0246	LR: 0.000800
Training Epoch: 4 [18176/58500]	Loss: 0.0328	LR: 0.000800
Training Epoch: 4 [18432/58500]	Loss: 0.0425	LR: 0.000800
Training Epoch: 4 [18688/58500]	Loss: 0.0344	LR: 0.000800
Training Epoch: 4 [18944/58500]	Loss: 0.0211	LR: 0.000800
Training Epoch: 4 [19200/58500]	Loss: 0.0430	LR: 0.000800
Training Epoch: 4 [19456/58500]	Loss: 0.0176	LR: 0.000800
Training Epoch: 4 [19712/58500]	Loss: 0.0185	LR: 0.000800
Training Epoch: 4 [19968/58500]	Loss: 0.0323	LR: 0.000800
Training Epoch: 4 [20224/58500]	Loss: 0.0266	LR: 0.000800
Training Epoch: 4 [20480/58500]	Loss: 0.0133	LR: 0.000800
Training Epoch: 4 [20736/58500]	Loss: 0.0179	LR: 0.000800
Training Epoch: 4 [20992/58500]	Loss: 0.0145	LR: 0.000800
Training Epoch: 4 [21248/58500]	Loss: 0.0199	LR: 0.000800
Training Epoch: 4 [21504/58500]	Loss: 0.0314	LR: 0.000800
Training Epoch: 4 [21760/58500]	Loss: 0.0271	LR: 0.000800
Training Epoch: 4 [22016/58500]	Loss: 0.0307	LR: 0.000800
Training Epoch: 4 [22272/58500]	Loss: 0.0274	LR: 0.000800
Training Epoch: 4 [22528/58500]	Loss: 0.0315	LR: 0.000800
Training Epoch: 4 [22784/58500]	Loss: 0.0266	LR: 0.000800
Training Epoch: 4 [23040/58500]	Loss: 0.0200	LR: 0.000800
Training Epoch: 4 [23296/58500]	Loss: 0.0159	LR: 0.000800
Training Epoch: 4 [23552/58500]	Loss: 0.0223	LR: 0.000800
Training Epoch: 4 [23808/58500]	Loss: 0.0526	LR: 0.000800
Training Epoch: 4 [24064/58500]	Loss: 0.0075	LR: 0.000800
Training Epoch: 4 [24320/58500]	Loss: 0.0417	LR: 0.000800
Training Epoch: 4 [24576/58500]	Loss: 0.0338	LR: 0.000800
Training Epoch: 4 [24832/58500]	Loss: 0.0157	LR: 0.000800
Training Epoch: 4 [25088/58500]	Loss: 0.0481	LR: 0.000800
Training Epoch: 4 [25344/58500]	Loss: 0.0234	LR: 0.000800
Training Epoch: 4 [25600/58500]	Loss: 0.0274	LR: 0.000800
Training Epoch: 4 [25856/58500]	Loss: 0.0152	LR: 0.000800
Training Epoch: 4 [26112/58500]	Loss: 0.0156	LR: 0.000800
Training Epoch: 4 [26368/58500]	Loss: 0.0430	LR: 0.000800
Training Epoch: 4 [26624/58500]	Loss: 0.0170	LR: 0.000800
Training Epoch: 4 [26880/58500]	Loss: 0.0396	LR: 0.000800
Training Epoch: 4 [27136/58500]	Loss: 0.0258	LR: 0.000800
Training Epoch: 4 [27392/58500]	Loss: 0.0157	LR: 0.000800
Training Epoch: 4 [27648/58500]	Loss: 0.0535	LR: 0.000800
Training Epoch: 4 [27904/58500]	Loss: 0.0172	LR: 0.000800
Training Epoch: 4 [28160/58500]	Loss: 0.0092	LR: 0.000800
Training Epoch: 4 [28416/58500]	Loss: 0.0213	LR: 0.000800
Training Epoch: 4 [28672/58500]	Loss: 0.0222	LR: 0.000800
Training Epoch: 4 [28928/58500]	Loss: 0.0120	LR: 0.000800
Training Epoch: 4 [29184/58500]	Loss: 0.0188	LR: 0.000800
Training Epoch: 4 [29440/58500]	Loss: 0.0235	LR: 0.000800
Training Epoch: 4 [29696/58500]	Loss: 0.0455	LR: 0.000800
Training Epoch: 4 [29952/58500]	Loss: 0.0218	LR: 0.000800
Training Epoch: 4 [30208/58500]	Loss: 0.0484	LR: 0.000800
Training Epoch: 4 [30464/58500]	Loss: 0.0264	LR: 0.000800
Training Epoch: 4 [30720/58500]	Loss: 0.0216	LR: 0.000800
Training Epoch: 4 [30976/58500]	Loss: 0.0249	LR: 0.000800
Training Epoch: 4 [31232/58500]	Loss: 0.0112	LR: 0.000800
Training Epoch: 4 [31488/58500]	Loss: 0.0204	LR: 0.000800
Training Epoch: 4 [31744/58500]	Loss: 0.0153	LR: 0.000800
Training Epoch: 4 [32000/58500]	Loss: 0.0194	LR: 0.000800
Training Epoch: 4 [32256/58500]	Loss: 0.0124	LR: 0.000800
Training Epoch: 4 [32512/58500]	Loss: 0.0267	LR: 0.000800
Training Epoch: 4 [32768/58500]	Loss: 0.0124	LR: 0.000800
Training Epoch: 4 [33024/58500]	Loss: 0.0552	LR: 0.000800
Training Epoch: 4 [33280/58500]	Loss: 0.0244	LR: 0.000800
Training Epoch: 4 [33536/58500]	Loss: 0.0262	LR: 0.000800
Training Epoch: 4 [33792/58500]	Loss: 0.0176	LR: 0.000800
Training Epoch: 4 [34048/58500]	Loss: 0.0043	LR: 0.000800
Training Epoch: 4 [34304/58500]	Loss: 0.0290	LR: 0.000800
Training Epoch: 4 [34560/58500]	Loss: 0.0196	LR: 0.000800
Training Epoch: 4 [34816/58500]	Loss: 0.0096	LR: 0.000800
Training Epoch: 4 [35072/58500]	Loss: 0.0122	LR: 0.000800
Training Epoch: 4 [35328/58500]	Loss: 0.0154	LR: 0.000800
Training Epoch: 4 [35584/58500]	Loss: 0.0334	LR: 0.000800
Training Epoch: 4 [35840/58500]	Loss: 0.0181	LR: 0.000800
Training Epoch: 4 [36096/58500]	Loss: 0.0077	LR: 0.000800
Training Epoch: 4 [36352/58500]	Loss: 0.0245	LR: 0.000800
Training Epoch: 4 [36608/58500]	Loss: 0.0177	LR: 0.000800
Training Epoch: 4 [36864/58500]	Loss: 0.0155	LR: 0.000800
Training Epoch: 4 [37120/58500]	Loss: 0.0140	LR: 0.000800
Training Epoch: 4 [37376/58500]	Loss: 0.0154	LR: 0.000800
Training Epoch: 4 [37632/58500]	Loss: 0.0270	LR: 0.000800
Training Epoch: 4 [37888/58500]	Loss: 0.0161	LR: 0.000800
Training Epoch: 4 [38144/58500]	Loss: 0.0540	LR: 0.000800
Training Epoch: 4 [38400/58500]	Loss: 0.0220	LR: 0.000800
Training Epoch: 4 [38656/58500]	Loss: 0.0230	LR: 0.000800
Training Epoch: 4 [38912/58500]	Loss: 0.0214	LR: 0.000800
Training Epoch: 4 [39168/58500]	Loss: 0.0254	LR: 0.000800
Training Epoch: 4 [39424/58500]	Loss: 0.0312	LR: 0.000800
Training Epoch: 4 [39680/58500]	Loss: 0.0126	LR: 0.000800
Training Epoch: 4 [39936/58500]	Loss: 0.0310	LR: 0.000800
Training Epoch: 4 [40192/58500]	Loss: 0.0137	LR: 0.000800
Training Epoch: 4 [40448/58500]	Loss: 0.0447	LR: 0.000800
Training Epoch: 4 [40704/58500]	Loss: 0.0109	LR: 0.000800
Training Epoch: 4 [40960/58500]	Loss: 0.0235	LR: 0.000800
Training Epoch: 4 [41216/58500]	Loss: 0.0204	LR: 0.000800
Training Epoch: 4 [41472/58500]	Loss: 0.0212	LR: 0.000800
Training Epoch: 4 [41728/58500]	Loss: 0.0181	LR: 0.000800
Training Epoch: 4 [41984/58500]	Loss: 0.0181	LR: 0.000800
Training Epoch: 4 [42240/58500]	Loss: 0.0577	LR: 0.000800
Training Epoch: 4 [42496/58500]	Loss: 0.0170	LR: 0.000800
Training Epoch: 4 [42752/58500]	Loss: 0.0270	LR: 0.000800
Training Epoch: 4 [43008/58500]	Loss: 0.0272	LR: 0.000800
Training Epoch: 4 [43264/58500]	Loss: 0.0627	LR: 0.000800
Training Epoch: 4 [43520/58500]	Loss: 0.0197	LR: 0.000800
Training Epoch: 4 [43776/58500]	Loss: 0.0081	LR: 0.000800
Training Epoch: 4 [44032/58500]	Loss: 0.0256	LR: 0.000800
Training Epoch: 4 [44288/58500]	Loss: 0.0101	LR: 0.000800
Training Epoch: 4 [44544/58500]	Loss: 0.0107	LR: 0.000800
Training Epoch: 4 [44800/58500]	Loss: 0.0310	LR: 0.000800
Training Epoch: 4 [45056/58500]	Loss: 0.0249	LR: 0.000800
Training Epoch: 4 [45312/58500]	Loss: 0.0210	LR: 0.000800
Training Epoch: 4 [45568/58500]	Loss: 0.0243	LR: 0.000800
Training Epoch: 4 [45824/58500]	Loss: 0.0356	LR: 0.000800
Training Epoch: 4 [46080/58500]	Loss: 0.0336	LR: 0.000800
Training Epoch: 4 [46336/58500]	Loss: 0.0202	LR: 0.000800
Training Epoch: 4 [46592/58500]	Loss: 0.0149	LR: 0.000800
Training Epoch: 4 [46848/58500]	Loss: 0.0170	LR: 0.000800
Training Epoch: 4 [47104/58500]	Loss: 0.0335	LR: 0.000800
Training Epoch: 4 [47360/58500]	Loss: 0.0153	LR: 0.000800
Training Epoch: 4 [47616/58500]	Loss: 0.0100	LR: 0.000800
Training Epoch: 4 [47872/58500]	Loss: 0.0231	LR: 0.000800
Training Epoch: 4 [48128/58500]	Loss: 0.0297	LR: 0.000800
Training Epoch: 4 [48384/58500]	Loss: 0.0323	LR: 0.000800
Training Epoch: 4 [48640/58500]	Loss: 0.0228	LR: 0.000800
Training Epoch: 4 [48896/58500]	Loss: 0.0128	LR: 0.000800
Training Epoch: 4 [49152/58500]	Loss: 0.0091	LR: 0.000800
Training Epoch: 4 [49408/58500]	Loss: 0.0177	LR: 0.000800
Training Epoch: 4 [49664/58500]	Loss: 0.0130	LR: 0.000800
Training Epoch: 4 [49920/58500]	Loss: 0.0181	LR: 0.000800
Training Epoch: 4 [50176/58500]	Loss: 0.0177	LR: 0.000800
Training Epoch: 4 [50432/58500]	Loss: 0.0194	LR: 0.000800
Training Epoch: 4 [50688/58500]	Loss: 0.0137	LR: 0.000800
Training Epoch: 4 [50944/58500]	Loss: 0.0516	LR: 0.000800
Training Epoch: 4 [51200/58500]	Loss: 0.0108	LR: 0.000800
Training Epoch: 4 [51456/58500]	Loss: 0.0613	LR: 0.000800
Training Epoch: 4 [51712/58500]	Loss: 0.0173	LR: 0.000800
Training Epoch: 4 [51968/58500]	Loss: 0.0296	LR: 0.000800
Training Epoch: 4 [52224/58500]	Loss: 0.0102	LR: 0.000800
Training Epoch: 4 [52480/58500]	Loss: 0.0420	LR: 0.000800
Training Epoch: 4 [52736/58500]	Loss: 0.0288	LR: 0.000800
Training Epoch: 4 [52992/58500]	Loss: 0.0074	LR: 0.000800
Training Epoch: 4 [53248/58500]	Loss: 0.0205	LR: 0.000800
Training Epoch: 4 [53504/58500]	Loss: 0.0223	LR: 0.000800
Training Epoch: 4 [53760/58500]	Loss: 0.0144	LR: 0.000800
Training Epoch: 4 [54016/58500]	Loss: 0.0168	LR: 0.000800
Training Epoch: 4 [54272/58500]	Loss: 0.0239	LR: 0.000800
Training Epoch: 4 [54528/58500]	Loss: 0.0107	LR: 0.000800
Training Epoch: 4 [54784/58500]	Loss: 0.0362	LR: 0.000800
Training Epoch: 4 [55040/58500]	Loss: 0.0335	LR: 0.000800
Training Epoch: 4 [55296/58500]	Loss: 0.0242	LR: 0.000800
Training Epoch: 4 [55552/58500]	Loss: 0.0200	LR: 0.000800
Training Epoch: 4 [55808/58500]	Loss: 0.0345	LR: 0.000800
Training Epoch: 4 [56064/58500]	Loss: 0.0285	LR: 0.000800
Training Epoch: 4 [56320/58500]	Loss: 0.0082	LR: 0.000800
Training Epoch: 4 [56576/58500]	Loss: 0.0270	LR: 0.000800
Training Epoch: 4 [56832/58500]	Loss: 0.0184	LR: 0.000800
Training Epoch: 4 [57088/58500]	Loss: 0.0252	LR: 0.000800
Training Epoch: 4 [57344/58500]	Loss: 0.0401	LR: 0.000800
Training Epoch: 4 [57600/58500]	Loss: 0.0059	LR: 0.000800
Training Epoch: 4 [57856/58500]	Loss: 0.0288	LR: 0.000800
Training Epoch: 4 [58112/58500]	Loss: 0.0201	LR: 0.000800
Training Epoch: 4 [58368/58500]	Loss: 0.0354	LR: 0.000800
Training Epoch: 4 [58500/58500]	Loss: 0.0340	LR: 0.000800
Epoch 4 - Average Train Loss: 0.0245, Train Accuracy: 0.9935
Epoch 4 training time consumed: 41.80s
Evaluating Network.....
Test set: Epoch: 4, Average loss: 0.0001, Accuracy: 0.9953, Time consumed:1.70s
Saving weights file to checkpoint/retrain/AllCNN/Wednesday_23_July_2025_07h_08m_27s/AllCNN-Mnist-seed9-ret75-4-best.pth
Training Epoch: 5 [256/58500]	Loss: 0.0112	LR: 0.000800
Training Epoch: 5 [512/58500]	Loss: 0.0169	LR: 0.000800
Training Epoch: 5 [768/58500]	Loss: 0.0205	LR: 0.000800
Training Epoch: 5 [1024/58500]	Loss: 0.0287	LR: 0.000800
Training Epoch: 5 [1280/58500]	Loss: 0.0279	LR: 0.000800
Training Epoch: 5 [1536/58500]	Loss: 0.0106	LR: 0.000800
Training Epoch: 5 [1792/58500]	Loss: 0.0378	LR: 0.000800
Training Epoch: 5 [2048/58500]	Loss: 0.0089	LR: 0.000800
Training Epoch: 5 [2304/58500]	Loss: 0.0234	LR: 0.000800
Training Epoch: 5 [2560/58500]	Loss: 0.0291	LR: 0.000800
Training Epoch: 5 [2816/58500]	Loss: 0.0199	LR: 0.000800
Training Epoch: 5 [3072/58500]	Loss: 0.0160	LR: 0.000800
Training Epoch: 5 [3328/58500]	Loss: 0.0435	LR: 0.000800
Training Epoch: 5 [3584/58500]	Loss: 0.0146	LR: 0.000800
Training Epoch: 5 [3840/58500]	Loss: 0.0282	LR: 0.000800
Training Epoch: 5 [4096/58500]	Loss: 0.0258	LR: 0.000800
Training Epoch: 5 [4352/58500]	Loss: 0.0275	LR: 0.000800
Training Epoch: 5 [4608/58500]	Loss: 0.0145	LR: 0.000800
Training Epoch: 5 [4864/58500]	Loss: 0.0451	LR: 0.000800
Training Epoch: 5 [5120/58500]	Loss: 0.0138	LR: 0.000800
Training Epoch: 5 [5376/58500]	Loss: 0.0316	LR: 0.000800
Training Epoch: 5 [5632/58500]	Loss: 0.0054	LR: 0.000800
Training Epoch: 5 [5888/58500]	Loss: 0.0064	LR: 0.000800
Training Epoch: 5 [6144/58500]	Loss: 0.0149	LR: 0.000800
Training Epoch: 5 [6400/58500]	Loss: 0.0394	LR: 0.000800
Training Epoch: 5 [6656/58500]	Loss: 0.0125	LR: 0.000800
Training Epoch: 5 [6912/58500]	Loss: 0.0222	LR: 0.000800
Training Epoch: 5 [7168/58500]	Loss: 0.0084	LR: 0.000800
Training Epoch: 5 [7424/58500]	Loss: 0.0304	LR: 0.000800
Training Epoch: 5 [7680/58500]	Loss: 0.0132	LR: 0.000800
Training Epoch: 5 [7936/58500]	Loss: 0.0233	LR: 0.000800
Training Epoch: 5 [8192/58500]	Loss: 0.0433	LR: 0.000800
Training Epoch: 5 [8448/58500]	Loss: 0.0297	LR: 0.000800
Training Epoch: 5 [8704/58500]	Loss: 0.0269	LR: 0.000800
Training Epoch: 5 [8960/58500]	Loss: 0.0375	LR: 0.000800
Training Epoch: 5 [9216/58500]	Loss: 0.0230	LR: 0.000800
Training Epoch: 5 [9472/58500]	Loss: 0.0221	LR: 0.000800
Training Epoch: 5 [9728/58500]	Loss: 0.0409	LR: 0.000800
Training Epoch: 5 [9984/58500]	Loss: 0.0252	LR: 0.000800
Training Epoch: 5 [10240/58500]	Loss: 0.0216	LR: 0.000800
Training Epoch: 5 [10496/58500]	Loss: 0.0410	LR: 0.000800
Training Epoch: 5 [10752/58500]	Loss: 0.0207	LR: 0.000800
Training Epoch: 5 [11008/58500]	Loss: 0.0226	LR: 0.000800
Training Epoch: 5 [11264/58500]	Loss: 0.0266	LR: 0.000800
Training Epoch: 5 [11520/58500]	Loss: 0.0356	LR: 0.000800
Training Epoch: 5 [11776/58500]	Loss: 0.0289	LR: 0.000800
Training Epoch: 5 [12032/58500]	Loss: 0.0106	LR: 0.000800
Training Epoch: 5 [12288/58500]	Loss: 0.0167	LR: 0.000800
Training Epoch: 5 [12544/58500]	Loss: 0.0253	LR: 0.000800
Training Epoch: 5 [12800/58500]	Loss: 0.0149	LR: 0.000800
Training Epoch: 5 [13056/58500]	Loss: 0.0411	LR: 0.000800
Training Epoch: 5 [13312/58500]	Loss: 0.0224	LR: 0.000800
Training Epoch: 5 [13568/58500]	Loss: 0.0184	LR: 0.000800
Training Epoch: 5 [13824/58500]	Loss: 0.0104	LR: 0.000800
Training Epoch: 5 [14080/58500]	Loss: 0.0140	LR: 0.000800
Training Epoch: 5 [14336/58500]	Loss: 0.0564	LR: 0.000800
Training Epoch: 5 [14592/58500]	Loss: 0.0370	LR: 0.000800
Training Epoch: 5 [14848/58500]	Loss: 0.0112	LR: 0.000800
Training Epoch: 5 [15104/58500]	Loss: 0.0244	LR: 0.000800
Training Epoch: 5 [15360/58500]	Loss: 0.0235	LR: 0.000800
Training Epoch: 5 [15616/58500]	Loss: 0.0153	LR: 0.000800
Training Epoch: 5 [15872/58500]	Loss: 0.0264	LR: 0.000800
Training Epoch: 5 [16128/58500]	Loss: 0.0185	LR: 0.000800
Training Epoch: 5 [16384/58500]	Loss: 0.0087	LR: 0.000800
Training Epoch: 5 [16640/58500]	Loss: 0.0552	LR: 0.000800
Training Epoch: 5 [16896/58500]	Loss: 0.0264	LR: 0.000800
Training Epoch: 5 [17152/58500]	Loss: 0.0304	LR: 0.000800
Training Epoch: 5 [17408/58500]	Loss: 0.0565	LR: 0.000800
Training Epoch: 5 [17664/58500]	Loss: 0.0098	LR: 0.000800
Training Epoch: 5 [17920/58500]	Loss: 0.0251	LR: 0.000800
Training Epoch: 5 [18176/58500]	Loss: 0.0210	LR: 0.000800
Training Epoch: 5 [18432/58500]	Loss: 0.0230	LR: 0.000800
Training Epoch: 5 [18688/58500]	Loss: 0.0287	LR: 0.000800
Training Epoch: 5 [18944/58500]	Loss: 0.0190	LR: 0.000800
Training Epoch: 5 [19200/58500]	Loss: 0.0324	LR: 0.000800
Training Epoch: 5 [19456/58500]	Loss: 0.0259	LR: 0.000800
Training Epoch: 5 [19712/58500]	Loss: 0.0329	LR: 0.000800
Training Epoch: 5 [19968/58500]	Loss: 0.0354	LR: 0.000800
Training Epoch: 5 [20224/58500]	Loss: 0.0179	LR: 0.000800
Training Epoch: 5 [20480/58500]	Loss: 0.0199	LR: 0.000800
Training Epoch: 5 [20736/58500]	Loss: 0.0141	LR: 0.000800
Training Epoch: 5 [20992/58500]	Loss: 0.0329	LR: 0.000800
Training Epoch: 5 [21248/58500]	Loss: 0.0140	LR: 0.000800
Training Epoch: 5 [21504/58500]	Loss: 0.0171	LR: 0.000800
Training Epoch: 5 [21760/58500]	Loss: 0.0188	LR: 0.000800
Training Epoch: 5 [22016/58500]	Loss: 0.0272	LR: 0.000800
Training Epoch: 5 [22272/58500]	Loss: 0.0062	LR: 0.000800
Training Epoch: 5 [22528/58500]	Loss: 0.0098	LR: 0.000800
Training Epoch: 5 [22784/58500]	Loss: 0.0527	LR: 0.000800
Training Epoch: 5 [23040/58500]	Loss: 0.0198	LR: 0.000800
Training Epoch: 5 [23296/58500]	Loss: 0.0088	LR: 0.000800
Training Epoch: 5 [23552/58500]	Loss: 0.0410	LR: 0.000800
Training Epoch: 5 [23808/58500]	Loss: 0.0135	LR: 0.000800
Training Epoch: 5 [24064/58500]	Loss: 0.0291	LR: 0.000800
Training Epoch: 5 [24320/58500]	Loss: 0.0423	LR: 0.000800
Training Epoch: 5 [24576/58500]	Loss: 0.0393	LR: 0.000800
Training Epoch: 5 [24832/58500]	Loss: 0.0308	LR: 0.000800
Training Epoch: 5 [25088/58500]	Loss: 0.0424	LR: 0.000800
Training Epoch: 5 [25344/58500]	Loss: 0.0114	LR: 0.000800
Training Epoch: 5 [25600/58500]	Loss: 0.0241	LR: 0.000800
Training Epoch: 5 [25856/58500]	Loss: 0.0257	LR: 0.000800
Training Epoch: 5 [26112/58500]	Loss: 0.0413	LR: 0.000800
Training Epoch: 5 [26368/58500]	Loss: 0.0692	LR: 0.000800
Training Epoch: 5 [26624/58500]	Loss: 0.0246	LR: 0.000800
Training Epoch: 5 [26880/58500]	Loss: 0.0410	LR: 0.000800
Training Epoch: 5 [27136/58500]	Loss: 0.0321	LR: 0.000800
Training Epoch: 5 [27392/58500]	Loss: 0.0316	LR: 0.000800
Training Epoch: 5 [27648/58500]	Loss: 0.0267	LR: 0.000800
Training Epoch: 5 [27904/58500]	Loss: 0.0360	LR: 0.000800
Training Epoch: 5 [28160/58500]	Loss: 0.0183	LR: 0.000800
Training Epoch: 5 [28416/58500]	Loss: 0.0313	LR: 0.000800
Training Epoch: 5 [28672/58500]	Loss: 0.0193	LR: 0.000800
Training Epoch: 5 [28928/58500]	Loss: 0.0164	LR: 0.000800
Training Epoch: 5 [29184/58500]	Loss: 0.0122	LR: 0.000800
Training Epoch: 5 [29440/58500]	Loss: 0.0202	LR: 0.000800
Training Epoch: 5 [29696/58500]	Loss: 0.0099	LR: 0.000800
Training Epoch: 5 [29952/58500]	Loss: 0.0465	LR: 0.000800
Training Epoch: 5 [30208/58500]	Loss: 0.0146	LR: 0.000800
Training Epoch: 5 [30464/58500]	Loss: 0.0103	LR: 0.000800
Training Epoch: 5 [30720/58500]	Loss: 0.0205	LR: 0.000800
Training Epoch: 5 [30976/58500]	Loss: 0.0111	LR: 0.000800
Training Epoch: 5 [31232/58500]	Loss: 0.0156	LR: 0.000800
Training Epoch: 5 [31488/58500]	Loss: 0.0255	LR: 0.000800
Training Epoch: 5 [31744/58500]	Loss: 0.0199	LR: 0.000800
Training Epoch: 5 [32000/58500]	Loss: 0.0349	LR: 0.000800
Training Epoch: 5 [32256/58500]	Loss: 0.0098	LR: 0.000800
Training Epoch: 5 [32512/58500]	Loss: 0.0311	LR: 0.000800
Training Epoch: 5 [32768/58500]	Loss: 0.0263	LR: 0.000800
Training Epoch: 5 [33024/58500]	Loss: 0.0171	LR: 0.000800
Training Epoch: 5 [33280/58500]	Loss: 0.0174	LR: 0.000800
Training Epoch: 5 [33536/58500]	Loss: 0.0194	LR: 0.000800
Training Epoch: 5 [33792/58500]	Loss: 0.0225	LR: 0.000800
Training Epoch: 5 [34048/58500]	Loss: 0.0100	LR: 0.000800
Training Epoch: 5 [34304/58500]	Loss: 0.0195	LR: 0.000800
Training Epoch: 5 [34560/58500]	Loss: 0.0219	LR: 0.000800
Training Epoch: 5 [34816/58500]	Loss: 0.0252	LR: 0.000800
Training Epoch: 5 [35072/58500]	Loss: 0.0132	LR: 0.000800
Training Epoch: 5 [35328/58500]	Loss: 0.0111	LR: 0.000800
Training Epoch: 5 [35584/58500]	Loss: 0.0197	LR: 0.000800
Training Epoch: 5 [35840/58500]	Loss: 0.0195	LR: 0.000800
Training Epoch: 5 [36096/58500]	Loss: 0.0180	LR: 0.000800
Training Epoch: 5 [36352/58500]	Loss: 0.0115	LR: 0.000800
Training Epoch: 5 [36608/58500]	Loss: 0.0209	LR: 0.000800
Training Epoch: 5 [36864/58500]	Loss: 0.0274	LR: 0.000800
Training Epoch: 5 [37120/58500]	Loss: 0.0322	LR: 0.000800
Training Epoch: 5 [37376/58500]	Loss: 0.0411	LR: 0.000800
Training Epoch: 5 [37632/58500]	Loss: 0.0362	LR: 0.000800
Training Epoch: 5 [37888/58500]	Loss: 0.0133	LR: 0.000800
Training Epoch: 5 [38144/58500]	Loss: 0.0085	LR: 0.000800
Training Epoch: 5 [38400/58500]	Loss: 0.0326	LR: 0.000800
Training Epoch: 5 [38656/58500]	Loss: 0.0087	LR: 0.000800
Training Epoch: 5 [38912/58500]	Loss: 0.0085	LR: 0.000800
Training Epoch: 5 [39168/58500]	Loss: 0.0258	LR: 0.000800
Training Epoch: 5 [39424/58500]	Loss: 0.0145	LR: 0.000800
Training Epoch: 5 [39680/58500]	Loss: 0.0232	LR: 0.000800
Training Epoch: 5 [39936/58500]	Loss: 0.0717	LR: 0.000800
Training Epoch: 5 [40192/58500]	Loss: 0.0167	LR: 0.000800
Training Epoch: 5 [40448/58500]	Loss: 0.0229	LR: 0.000800
Training Epoch: 5 [40704/58500]	Loss: 0.0194	LR: 0.000800
Training Epoch: 5 [40960/58500]	Loss: 0.0251	LR: 0.000800
Training Epoch: 5 [41216/58500]	Loss: 0.0173	LR: 0.000800
Training Epoch: 5 [41472/58500]	Loss: 0.0081	LR: 0.000800
Training Epoch: 5 [41728/58500]	Loss: 0.0151	LR: 0.000800
Training Epoch: 5 [41984/58500]	Loss: 0.0556	LR: 0.000800
Training Epoch: 5 [42240/58500]	Loss: 0.0304	LR: 0.000800
Training Epoch: 5 [42496/58500]	Loss: 0.0205	LR: 0.000800
Training Epoch: 5 [42752/58500]	Loss: 0.0141	LR: 0.000800
Training Epoch: 5 [43008/58500]	Loss: 0.0391	LR: 0.000800
Training Epoch: 5 [43264/58500]	Loss: 0.0232	LR: 0.000800
Training Epoch: 5 [43520/58500]	Loss: 0.0163	LR: 0.000800
Training Epoch: 5 [43776/58500]	Loss: 0.0253	LR: 0.000800
Training Epoch: 5 [44032/58500]	Loss: 0.0449	LR: 0.000800
Training Epoch: 5 [44288/58500]	Loss: 0.0329	LR: 0.000800
Training Epoch: 5 [44544/58500]	Loss: 0.0168	LR: 0.000800
Training Epoch: 5 [44800/58500]	Loss: 0.0087	LR: 0.000800
Training Epoch: 5 [45056/58500]	Loss: 0.0125	LR: 0.000800
Training Epoch: 5 [45312/58500]	Loss: 0.0338	LR: 0.000800
Training Epoch: 5 [45568/58500]	Loss: 0.0317	LR: 0.000800
Training Epoch: 5 [45824/58500]	Loss: 0.0279	LR: 0.000800
Training Epoch: 5 [46080/58500]	Loss: 0.0172	LR: 0.000800
Training Epoch: 5 [46336/58500]	Loss: 0.0114	LR: 0.000800
Training Epoch: 5 [46592/58500]	Loss: 0.0142	LR: 0.000800
Training Epoch: 5 [46848/58500]	Loss: 0.0216	LR: 0.000800
Training Epoch: 5 [47104/58500]	Loss: 0.0082	LR: 0.000800
Training Epoch: 5 [47360/58500]	Loss: 0.0185	LR: 0.000800
Training Epoch: 5 [47616/58500]	Loss: 0.0114	LR: 0.000800
Training Epoch: 5 [47872/58500]	Loss: 0.0197	LR: 0.000800
Training Epoch: 5 [48128/58500]	Loss: 0.0122	LR: 0.000800
Training Epoch: 5 [48384/58500]	Loss: 0.0144	LR: 0.000800
Training Epoch: 5 [48640/58500]	Loss: 0.0357	LR: 0.000800
Training Epoch: 5 [48896/58500]	Loss: 0.0163	LR: 0.000800
Training Epoch: 5 [49152/58500]	Loss: 0.0214	LR: 0.000800
Training Epoch: 5 [49408/58500]	Loss: 0.0159	LR: 0.000800
Training Epoch: 5 [49664/58500]	Loss: 0.0229	LR: 0.000800
Training Epoch: 5 [49920/58500]	Loss: 0.0150	LR: 0.000800
Training Epoch: 5 [50176/58500]	Loss: 0.0157	LR: 0.000800
Training Epoch: 5 [50432/58500]	Loss: 0.0229	LR: 0.000800
Training Epoch: 5 [50688/58500]	Loss: 0.0108	LR: 0.000800
Training Epoch: 5 [50944/58500]	Loss: 0.0224	LR: 0.000800
Training Epoch: 5 [51200/58500]	Loss: 0.0217	LR: 0.000800
Training Epoch: 5 [51456/58500]	Loss: 0.0439	LR: 0.000800
Training Epoch: 5 [51712/58500]	Loss: 0.0162	LR: 0.000800
Training Epoch: 5 [51968/58500]	Loss: 0.0183	LR: 0.000800
Training Epoch: 5 [52224/58500]	Loss: 0.0226	LR: 0.000800
Training Epoch: 5 [52480/58500]	Loss: 0.0658	LR: 0.000800
Training Epoch: 5 [52736/58500]	Loss: 0.0275	LR: 0.000800
Training Epoch: 5 [52992/58500]	Loss: 0.0411	LR: 0.000800
Training Epoch: 5 [53248/58500]	Loss: 0.0181	LR: 0.000800
Training Epoch: 5 [53504/58500]	Loss: 0.0289	LR: 0.000800
Training Epoch: 5 [53760/58500]	Loss: 0.0182	LR: 0.000800
Training Epoch: 5 [54016/58500]	Loss: 0.0232	LR: 0.000800
Training Epoch: 5 [54272/58500]	Loss: 0.0192	LR: 0.000800
Training Epoch: 5 [54528/58500]	Loss: 0.0110	LR: 0.000800
Training Epoch: 5 [54784/58500]	Loss: 0.0161	LR: 0.000800
Training Epoch: 5 [55040/58500]	Loss: 0.0326	LR: 0.000800
Training Epoch: 5 [55296/58500]	Loss: 0.0169	LR: 0.000800
Training Epoch: 5 [55552/58500]	Loss: 0.0270	LR: 0.000800
Training Epoch: 5 [55808/58500]	Loss: 0.0298	LR: 0.000800
Training Epoch: 5 [56064/58500]	Loss: 0.0204	LR: 0.000800
Training Epoch: 5 [56320/58500]	Loss: 0.0084	LR: 0.000800
Training Epoch: 5 [56576/58500]	Loss: 0.0188	LR: 0.000800
Training Epoch: 5 [56832/58500]	Loss: 0.0101	LR: 0.000800
Training Epoch: 5 [57088/58500]	Loss: 0.0217	LR: 0.000800
Training Epoch: 5 [57344/58500]	Loss: 0.0244	LR: 0.000800
Training Epoch: 5 [57600/58500]	Loss: 0.0387	LR: 0.000800
Training Epoch: 5 [57856/58500]	Loss: 0.0400	LR: 0.000800
Training Epoch: 5 [58112/58500]	Loss: 0.0085	LR: 0.000800
Training Epoch: 5 [58368/58500]	Loss: 0.0061	LR: 0.000800
Training Epoch: 5 [58500/58500]	Loss: 0.0320	LR: 0.000800
Epoch 5 - Average Train Loss: 0.0237, Train Accuracy: 0.9935
Epoch 5 training time consumed: 41.71s
Evaluating Network.....
Test set: Epoch: 5, Average loss: 0.0001, Accuracy: 0.9952, Time consumed:1.70s
Valid (Test) Dl:  10000
Train Dl:  60000
Retain Train Dl:  58500
Forget Train Dl:  1500
Retain Valid Dl:  58500
Forget Valid Dl:  1500
retain_prob Distribution: 10000 samples
test_prob Distribution: 10000 samples
forget_prob Distribution: 1500 samples
Set1 Distribution: 1500 samples
Set2 Distribution: 1500 samples
Set1 Distribution: 1500 samples
Set2 Distribution: 1500 samples
Set1 Distribution: 10000 samples
Set2 Distribution: 10000 samples
Set1 Distribution: 10000 samples
Set2 Distribution: 10000 samples
Test Accuracy: 99.53125
Retain Accuracy: 99.43548583984375
Zero-Retain Forget (ZRF): 0.8014712333679199
Membership Inference Attack (MIA): 0.17
Forget vs Retain Membership Inference Attack (MIA): 0.47833333333333333
Forget vs Test Membership Inference Attack (MIA): 0.47833333333333333
Test vs Retain Membership Inference Attack (MIA): 0.485
Train vs Test Membership Inference Attack (MIA): 0.49525
Forget Set Accuracy (Df): 99.46851348876953
Method Execution Time: 869.44 seconds
