
📌S Retain class distribution for seed 8:
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 8:
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
77=97

📊 Updated class distribution:
Retain set:
  Class 0: 5623
  Class 1: 6442
  Class 2: 5658
  Class 3: 5831
  Class 4: 5542
  Class 5: 5121
  Class 6: 5618
  Class 7: 5965
  Class 8: 5551
  Class 9: 5649
Forget set:
  Class 0: 300
  Class 1: 300
  Class 2: 300
  Class 3: 300
  Class 4: 300
  Class 5: 300
  Class 6: 300
  Class 7: 300
  Class 8: 300
  Class 9: 300
⚠️ Warning: Retain train loader may not be shuffled.
Training Epoch: 1 [256/57000]	Loss: 2.3150	LR: 0.000000
Training Epoch: 1 [512/57000]	Loss: 2.3034	LR: 0.000448
Training Epoch: 1 [768/57000]	Loss: 2.3178	LR: 0.000897
Training Epoch: 1 [1024/57000]	Loss: 2.3006	LR: 0.001345
Training Epoch: 1 [1280/57000]	Loss: 2.2822	LR: 0.001794
Training Epoch: 1 [1536/57000]	Loss: 2.2921	LR: 0.002242
Training Epoch: 1 [1792/57000]	Loss: 2.3017	LR: 0.002691
Training Epoch: 1 [2048/57000]	Loss: 2.2758	LR: 0.003139
Training Epoch: 1 [2304/57000]	Loss: 2.2734	LR: 0.003587
Training Epoch: 1 [2560/57000]	Loss: 2.2501	LR: 0.004036
Training Epoch: 1 [2816/57000]	Loss: 2.2298	LR: 0.004484
Training Epoch: 1 [3072/57000]	Loss: 2.2342	LR: 0.004933
Training Epoch: 1 [3328/57000]	Loss: 2.1973	LR: 0.005381
Training Epoch: 1 [3584/57000]	Loss: 2.1855	LR: 0.005830
Training Epoch: 1 [3840/57000]	Loss: 2.1849	LR: 0.006278
Training Epoch: 1 [4096/57000]	Loss: 2.1371	LR: 0.006726
Training Epoch: 1 [4352/57000]	Loss: 2.1132	LR: 0.007175
Training Epoch: 1 [4608/57000]	Loss: 2.1281	LR: 0.007623
Training Epoch: 1 [4864/57000]	Loss: 2.0974	LR: 0.008072
Training Epoch: 1 [5120/57000]	Loss: 2.0683	LR: 0.008520
Training Epoch: 1 [5376/57000]	Loss: 2.0157	LR: 0.008969
Training Epoch: 1 [5632/57000]	Loss: 2.0141	LR: 0.009417
Training Epoch: 1 [5888/57000]	Loss: 1.9951	LR: 0.009865
Training Epoch: 1 [6144/57000]	Loss: 1.9760	LR: 0.010314
Training Epoch: 1 [6400/57000]	Loss: 1.9152	LR: 0.010762
Training Epoch: 1 [6656/57000]	Loss: 1.8911	LR: 0.011211
Training Epoch: 1 [6912/57000]	Loss: 1.8547	LR: 0.011659
Training Epoch: 1 [7168/57000]	Loss: 1.7821	LR: 0.012108
Training Epoch: 1 [7424/57000]	Loss: 1.7588	LR: 0.012556
Training Epoch: 1 [7680/57000]	Loss: 1.7822	LR: 0.013004
Training Epoch: 1 [7936/57000]	Loss: 1.7152	LR: 0.013453
Training Epoch: 1 [8192/57000]	Loss: 1.6874	LR: 0.013901
Training Epoch: 1 [8448/57000]	Loss: 1.5925	LR: 0.014350
Training Epoch: 1 [8704/57000]	Loss: 1.6203	LR: 0.014798
Training Epoch: 1 [8960/57000]	Loss: 1.5075	LR: 0.015247
Training Epoch: 1 [9216/57000]	Loss: 1.4009	LR: 0.015695
Training Epoch: 1 [9472/57000]	Loss: 1.4349	LR: 0.016143
Training Epoch: 1 [9728/57000]	Loss: 1.3295	LR: 0.016592
Training Epoch: 1 [9984/57000]	Loss: 1.3285	LR: 0.017040
Training Epoch: 1 [10240/57000]	Loss: 1.2732	LR: 0.017489
Training Epoch: 1 [10496/57000]	Loss: 1.1785	LR: 0.017937
Training Epoch: 1 [10752/57000]	Loss: 1.1014	LR: 0.018386
Training Epoch: 1 [11008/57000]	Loss: 1.1239	LR: 0.018834
Training Epoch: 1 [11264/57000]	Loss: 1.0244	LR: 0.019283
Training Epoch: 1 [11520/57000]	Loss: 0.9436	LR: 0.019731
Training Epoch: 1 [11776/57000]	Loss: 0.9636	LR: 0.020179
Training Epoch: 1 [12032/57000]	Loss: 0.8642	LR: 0.020628
Training Epoch: 1 [12288/57000]	Loss: 0.8176	LR: 0.021076
Training Epoch: 1 [12544/57000]	Loss: 0.7556	LR: 0.021525
Training Epoch: 1 [12800/57000]	Loss: 0.7219	LR: 0.021973
Training Epoch: 1 [13056/57000]	Loss: 0.6659	LR: 0.022422
Training Epoch: 1 [13312/57000]	Loss: 0.6981	LR: 0.022870
Training Epoch: 1 [13568/57000]	Loss: 0.6429	LR: 0.023318
Training Epoch: 1 [13824/57000]	Loss: 0.5051	LR: 0.023767
Training Epoch: 1 [14080/57000]	Loss: 0.5593	LR: 0.024215
Training Epoch: 1 [14336/57000]	Loss: 0.4956	LR: 0.024664
Training Epoch: 1 [14592/57000]	Loss: 0.3857	LR: 0.025112
Training Epoch: 1 [14848/57000]	Loss: 0.4094	LR: 0.025561
Training Epoch: 1 [15104/57000]	Loss: 0.3054	LR: 0.026009
Training Epoch: 1 [15360/57000]	Loss: 0.4039	LR: 0.026457
Training Epoch: 1 [15616/57000]	Loss: 0.3838	LR: 0.026906
Training Epoch: 1 [15872/57000]	Loss: 0.3333	LR: 0.027354
Training Epoch: 1 [16128/57000]	Loss: 0.3235	LR: 0.027803
Training Epoch: 1 [16384/57000]	Loss: 0.3547	LR: 0.028251
Training Epoch: 1 [16640/57000]	Loss: 0.3190	LR: 0.028700
Training Epoch: 1 [16896/57000]	Loss: 0.3108	LR: 0.029148
Training Epoch: 1 [17152/57000]	Loss: 0.2602	LR: 0.029596
Training Epoch: 1 [17408/57000]	Loss: 0.3235	LR: 0.030045
Training Epoch: 1 [17664/57000]	Loss: 0.2863	LR: 0.030493
Training Epoch: 1 [17920/57000]	Loss: 0.2227	LR: 0.030942
Training Epoch: 1 [18176/57000]	Loss: 0.2618	LR: 0.031390
Training Epoch: 1 [18432/57000]	Loss: 0.1797	LR: 0.031839
Training Epoch: 1 [18688/57000]	Loss: 0.1815	LR: 0.032287
Training Epoch: 1 [18944/57000]	Loss: 0.2249	LR: 0.032735
Training Epoch: 1 [19200/57000]	Loss: 0.2146	LR: 0.033184
Training Epoch: 1 [19456/57000]	Loss: 0.1734	LR: 0.033632
Training Epoch: 1 [19712/57000]	Loss: 0.1425	LR: 0.034081
Training Epoch: 1 [19968/57000]	Loss: 0.2131	LR: 0.034529
Training Epoch: 1 [20224/57000]	Loss: 0.1660	LR: 0.034978
Training Epoch: 1 [20480/57000]	Loss: 0.2119	LR: 0.035426
Training Epoch: 1 [20736/57000]	Loss: 0.2255	LR: 0.035874
Training Epoch: 1 [20992/57000]	Loss: 0.1913	LR: 0.036323
Training Epoch: 1 [21248/57000]	Loss: 0.1895	LR: 0.036771
Training Epoch: 1 [21504/57000]	Loss: 0.1084	LR: 0.037220
Training Epoch: 1 [21760/57000]	Loss: 0.2171	LR: 0.037668
Training Epoch: 1 [22016/57000]	Loss: 0.1819	LR: 0.038117
Training Epoch: 1 [22272/57000]	Loss: 0.1773	LR: 0.038565
Training Epoch: 1 [22528/57000]	Loss: 0.1527	LR: 0.039013
Training Epoch: 1 [22784/57000]	Loss: 0.1927	LR: 0.039462
Training Epoch: 1 [23040/57000]	Loss: 0.1472	LR: 0.039910
Training Epoch: 1 [23296/57000]	Loss: 0.1672	LR: 0.040359
Training Epoch: 1 [23552/57000]	Loss: 0.1505	LR: 0.040807
Training Epoch: 1 [23808/57000]	Loss: 0.1482	LR: 0.041256
Training Epoch: 1 [24064/57000]	Loss: 0.1510	LR: 0.041704
Training Epoch: 1 [24320/57000]	Loss: 0.2263	LR: 0.042152
Training Epoch: 1 [24576/57000]	Loss: 0.1616	LR: 0.042601
Training Epoch: 1 [24832/57000]	Loss: 0.1878	LR: 0.043049
Training Epoch: 1 [25088/57000]	Loss: 0.1563	LR: 0.043498
Training Epoch: 1 [25344/57000]	Loss: 0.1455	LR: 0.043946
Training Epoch: 1 [25600/57000]	Loss: 0.1697	LR: 0.044395
Training Epoch: 1 [25856/57000]	Loss: 0.1458	LR: 0.044843
Training Epoch: 1 [26112/57000]	Loss: 0.1596	LR: 0.045291
Training Epoch: 1 [26368/57000]	Loss: 0.1408	LR: 0.045740
Training Epoch: 1 [26624/57000]	Loss: 0.1298	LR: 0.046188
Training Epoch: 1 [26880/57000]	Loss: 0.0982	LR: 0.046637
Training Epoch: 1 [27136/57000]	Loss: 0.1258	LR: 0.047085
Training Epoch: 1 [27392/57000]	Loss: 0.1450	LR: 0.047534
Training Epoch: 1 [27648/57000]	Loss: 0.1137	LR: 0.047982
Training Epoch: 1 [27904/57000]	Loss: 0.1364	LR: 0.048430
Training Epoch: 1 [28160/57000]	Loss: 0.1344	LR: 0.048879
Training Epoch: 1 [28416/57000]	Loss: 0.0941	LR: 0.049327
Training Epoch: 1 [28672/57000]	Loss: 0.1362	LR: 0.049776
Training Epoch: 1 [28928/57000]	Loss: 0.1199	LR: 0.050224
Training Epoch: 1 [29184/57000]	Loss: 0.0953	LR: 0.050673
Training Epoch: 1 [29440/57000]	Loss: 0.1048	LR: 0.051121
Training Epoch: 1 [29696/57000]	Loss: 0.0848	LR: 0.051570
Training Epoch: 1 [29952/57000]	Loss: 0.1339	LR: 0.052018
Training Epoch: 1 [30208/57000]	Loss: 0.1345	LR: 0.052466
Training Epoch: 1 [30464/57000]	Loss: 0.1757	LR: 0.052915
Training Epoch: 1 [30720/57000]	Loss: 0.0964	LR: 0.053363
Training Epoch: 1 [30976/57000]	Loss: 0.1366	LR: 0.053812
Training Epoch: 1 [31232/57000]	Loss: 0.1613	LR: 0.054260
Training Epoch: 1 [31488/57000]	Loss: 0.1363	LR: 0.054709
Training Epoch: 1 [31744/57000]	Loss: 0.1031	LR: 0.055157
Training Epoch: 1 [32000/57000]	Loss: 0.1078	LR: 0.055605
Training Epoch: 1 [32256/57000]	Loss: 0.1069	LR: 0.056054
Training Epoch: 1 [32512/57000]	Loss: 0.0991	LR: 0.056502
Training Epoch: 1 [32768/57000]	Loss: 0.0949	LR: 0.056951
Training Epoch: 1 [33024/57000]	Loss: 0.0605	LR: 0.057399
Training Epoch: 1 [33280/57000]	Loss: 0.1012	LR: 0.057848
Training Epoch: 1 [33536/57000]	Loss: 0.1121	LR: 0.058296
Training Epoch: 1 [33792/57000]	Loss: 0.1169	LR: 0.058744
Training Epoch: 1 [34048/57000]	Loss: 0.1340	LR: 0.059193
Training Epoch: 1 [34304/57000]	Loss: 0.0707	LR: 0.059641
Training Epoch: 1 [34560/57000]	Loss: 0.1228	LR: 0.060090
Training Epoch: 1 [34816/57000]	Loss: 0.0826	LR: 0.060538
Training Epoch: 1 [35072/57000]	Loss: 0.1051	LR: 0.060987
Training Epoch: 1 [35328/57000]	Loss: 0.0754	LR: 0.061435
Training Epoch: 1 [35584/57000]	Loss: 0.1026	LR: 0.061883
Training Epoch: 1 [35840/57000]	Loss: 0.0822	LR: 0.062332
Training Epoch: 1 [36096/57000]	Loss: 0.0495	LR: 0.062780
Training Epoch: 1 [36352/57000]	Loss: 0.0894	LR: 0.063229
Training Epoch: 1 [36608/57000]	Loss: 0.0697	LR: 0.063677
Training Epoch: 1 [36864/57000]	Loss: 0.1076	LR: 0.064126
Training Epoch: 1 [37120/57000]	Loss: 0.1244	LR: 0.064574
Training Epoch: 1 [37376/57000]	Loss: 0.0581	LR: 0.065022
Training Epoch: 1 [37632/57000]	Loss: 0.0536	LR: 0.065471
Training Epoch: 1 [37888/57000]	Loss: 0.0893	LR: 0.065919
Training Epoch: 1 [38144/57000]	Loss: 0.1170	LR: 0.066368
Training Epoch: 1 [38400/57000]	Loss: 0.0786	LR: 0.066816
Training Epoch: 1 [38656/57000]	Loss: 0.0816	LR: 0.067265
Training Epoch: 1 [38912/57000]	Loss: 0.1166	LR: 0.067713
Training Epoch: 1 [39168/57000]	Loss: 0.1040	LR: 0.068161
Training Epoch: 1 [39424/57000]	Loss: 0.1039	LR: 0.068610
Training Epoch: 1 [39680/57000]	Loss: 0.1009	LR: 0.069058
Training Epoch: 1 [39936/57000]	Loss: 0.0642	LR: 0.069507
Training Epoch: 1 [40192/57000]	Loss: 0.1311	LR: 0.069955
Training Epoch: 1 [40448/57000]	Loss: 0.1001	LR: 0.070404
Training Epoch: 1 [40704/57000]	Loss: 0.0807	LR: 0.070852
Training Epoch: 1 [40960/57000]	Loss: 0.0746	LR: 0.071300
Training Epoch: 1 [41216/57000]	Loss: 0.0976	LR: 0.071749
Training Epoch: 1 [41472/57000]	Loss: 0.0906	LR: 0.072197
Training Epoch: 1 [41728/57000]	Loss: 0.1155	LR: 0.072646
Training Epoch: 1 [41984/57000]	Loss: 0.1320	LR: 0.073094
Training Epoch: 1 [42240/57000]	Loss: 0.1124	LR: 0.073543
Training Epoch: 1 [42496/57000]	Loss: 0.1184	LR: 0.073991
Training Epoch: 1 [42752/57000]	Loss: 0.1004	LR: 0.074439
Training Epoch: 1 [43008/57000]	Loss: 0.0915	LR: 0.074888
Training Epoch: 1 [43264/57000]	Loss: 0.0635	LR: 0.075336
Training Epoch: 1 [43520/57000]	Loss: 0.0994	LR: 0.075785
Training Epoch: 1 [43776/57000]	Loss: 0.1064	LR: 0.076233
Training Epoch: 1 [44032/57000]	Loss: 0.0895	LR: 0.076682
Training Epoch: 1 [44288/57000]	Loss: 0.0714	LR: 0.077130
Training Epoch: 1 [44544/57000]	Loss: 0.0546	LR: 0.077578
Training Epoch: 1 [44800/57000]	Loss: 0.0521	LR: 0.078027
Training Epoch: 1 [45056/57000]	Loss: 0.0635	LR: 0.078475
Training Epoch: 1 [45312/57000]	Loss: 0.1130	LR: 0.078924
Training Epoch: 1 [45568/57000]	Loss: 0.0655	LR: 0.079372
Training Epoch: 1 [45824/57000]	Loss: 0.1069	LR: 0.079821
Training Epoch: 1 [46080/57000]	Loss: 0.0867	LR: 0.080269
Training Epoch: 1 [46336/57000]	Loss: 0.0618	LR: 0.080717
Training Epoch: 1 [46592/57000]	Loss: 0.0602	LR: 0.081166
Training Epoch: 1 [46848/57000]	Loss: 0.1066	LR: 0.081614
Training Epoch: 1 [47104/57000]	Loss: 0.1273	LR: 0.082063
Training Epoch: 1 [47360/57000]	Loss: 0.0831	LR: 0.082511
Training Epoch: 1 [47616/57000]	Loss: 0.0790	LR: 0.082960
Training Epoch: 1 [47872/57000]	Loss: 0.1161	LR: 0.083408
Training Epoch: 1 [48128/57000]	Loss: 0.0856	LR: 0.083857
Training Epoch: 1 [48384/57000]	Loss: 0.0749	LR: 0.084305
Training Epoch: 1 [48640/57000]	Loss: 0.1166	LR: 0.084753
Training Epoch: 1 [48896/57000]	Loss: 0.1244	LR: 0.085202
Training Epoch: 1 [49152/57000]	Loss: 0.1003	LR: 0.085650
Training Epoch: 1 [49408/57000]	Loss: 0.0574	LR: 0.086099
Training Epoch: 1 [49664/57000]	Loss: 0.1077	LR: 0.086547
Training Epoch: 1 [49920/57000]	Loss: 0.1132	LR: 0.086996
Training Epoch: 1 [50176/57000]	Loss: 0.0829	LR: 0.087444
Training Epoch: 1 [50432/57000]	Loss: 0.0716	LR: 0.087892
Training Epoch: 1 [50688/57000]	Loss: 0.0573	LR: 0.088341
Training Epoch: 1 [50944/57000]	Loss: 0.0840	LR: 0.088789
Training Epoch: 1 [51200/57000]	Loss: 0.0466	LR: 0.089238
Training Epoch: 1 [51456/57000]	Loss: 0.0865	LR: 0.089686
Training Epoch: 1 [51712/57000]	Loss: 0.1194	LR: 0.090135
Training Epoch: 1 [51968/57000]	Loss: 0.0754	LR: 0.090583
Training Epoch: 1 [52224/57000]	Loss: 0.0744	LR: 0.091031
Training Epoch: 1 [52480/57000]	Loss: 0.0890	LR: 0.091480
Training Epoch: 1 [52736/57000]	Loss: 0.1010	LR: 0.091928
Training Epoch: 1 [52992/57000]	Loss: 0.0508	LR: 0.092377
Training Epoch: 1 [53248/57000]	Loss: 0.0747	LR: 0.092825
Training Epoch: 1 [53504/57000]	Loss: 0.0610	LR: 0.093274
Training Epoch: 1 [53760/57000]	Loss: 0.0948	LR: 0.093722
Training Epoch: 1 [54016/57000]	Loss: 0.0496	LR: 0.094170
Training Epoch: 1 [54272/57000]	Loss: 0.0682	LR: 0.094619
Training Epoch: 1 [54528/57000]	Loss: 0.0732	LR: 0.095067
Training Epoch: 1 [54784/57000]	Loss: 0.1420	LR: 0.095516
Training Epoch: 1 [55040/57000]	Loss: 0.0862	LR: 0.095964
Training Epoch: 1 [55296/57000]	Loss: 0.0974	LR: 0.096413
Training Epoch: 1 [55552/57000]	Loss: 0.0374	LR: 0.096861
Training Epoch: 1 [55808/57000]	Loss: 0.0647	LR: 0.097309
Training Epoch: 1 [56064/57000]	Loss: 0.0902	LR: 0.097758
Training Epoch: 1 [56320/57000]	Loss: 0.0666	LR: 0.098206
Training Epoch: 1 [56576/57000]	Loss: 0.0893	LR: 0.098655
Training Epoch: 1 [56832/57000]	Loss: 0.0656	LR: 0.099103
Training Epoch: 1 [57000/57000]	Loss: 0.0356	LR: 0.099552
Epoch 1 - Average Train Loss: 0.5086, Train Accuracy: 0.8575
Epoch 1 training time consumed: 40.83s
Evaluating Network.....
Test set: Epoch: 1, Average loss: 0.0006, Accuracy: 0.9507, Time consumed:1.79s
Saving weights file to checkpoint/retrain/AllCNN/Wednesday_23_July_2025_17h_10m_19s/AllCNN-Mnist-seed8-ret50-1-best.pth
Training Epoch: 2 [256/57000]	Loss: 0.0707	LR: 0.020000
Training Epoch: 2 [512/57000]	Loss: 0.0612	LR: 0.020000
Training Epoch: 2 [768/57000]	Loss: 0.0631	LR: 0.020000
Training Epoch: 2 [1024/57000]	Loss: 0.0832	LR: 0.020000
Training Epoch: 2 [1280/57000]	Loss: 0.0498	LR: 0.020000
Training Epoch: 2 [1536/57000]	Loss: 0.0420	LR: 0.020000
Training Epoch: 2 [1792/57000]	Loss: 0.0694	LR: 0.020000
Training Epoch: 2 [2048/57000]	Loss: 0.0539	LR: 0.020000
Training Epoch: 2 [2304/57000]	Loss: 0.0598	LR: 0.020000
Training Epoch: 2 [2560/57000]	Loss: 0.0438	LR: 0.020000
Training Epoch: 2 [2816/57000]	Loss: 0.0569	LR: 0.020000
Training Epoch: 2 [3072/57000]	Loss: 0.0425	LR: 0.020000
Training Epoch: 2 [3328/57000]	Loss: 0.0837	LR: 0.020000
Training Epoch: 2 [3584/57000]	Loss: 0.0374	LR: 0.020000
Training Epoch: 2 [3840/57000]	Loss: 0.0808	LR: 0.020000
Training Epoch: 2 [4096/57000]	Loss: 0.0451	LR: 0.020000
Training Epoch: 2 [4352/57000]	Loss: 0.0791	LR: 0.020000
Training Epoch: 2 [4608/57000]	Loss: 0.0186	LR: 0.020000
Training Epoch: 2 [4864/57000]	Loss: 0.0543	LR: 0.020000
Training Epoch: 2 [5120/57000]	Loss: 0.0324	LR: 0.020000
Training Epoch: 2 [5376/57000]	Loss: 0.0264	LR: 0.020000
Training Epoch: 2 [5632/57000]	Loss: 0.0329	LR: 0.020000
Training Epoch: 2 [5888/57000]	Loss: 0.0463	LR: 0.020000
Training Epoch: 2 [6144/57000]	Loss: 0.0408	LR: 0.020000
Training Epoch: 2 [6400/57000]	Loss: 0.0438	LR: 0.020000
Training Epoch: 2 [6656/57000]	Loss: 0.0458	LR: 0.020000
Training Epoch: 2 [6912/57000]	Loss: 0.0706	LR: 0.020000
Training Epoch: 2 [7168/57000]	Loss: 0.0665	LR: 0.020000
Training Epoch: 2 [7424/57000]	Loss: 0.0544	LR: 0.020000
Training Epoch: 2 [7680/57000]	Loss: 0.0606	LR: 0.020000
Training Epoch: 2 [7936/57000]	Loss: 0.0384	LR: 0.020000
Training Epoch: 2 [8192/57000]	Loss: 0.0311	LR: 0.020000
Training Epoch: 2 [8448/57000]	Loss: 0.0607	LR: 0.020000
Training Epoch: 2 [8704/57000]	Loss: 0.0269	LR: 0.020000
Training Epoch: 2 [8960/57000]	Loss: 0.0375	LR: 0.020000
Training Epoch: 2 [9216/57000]	Loss: 0.0751	LR: 0.020000
Training Epoch: 2 [9472/57000]	Loss: 0.0343	LR: 0.020000
Training Epoch: 2 [9728/57000]	Loss: 0.0398	LR: 0.020000
Training Epoch: 2 [9984/57000]	Loss: 0.0392	LR: 0.020000
Training Epoch: 2 [10240/57000]	Loss: 0.0381	LR: 0.020000
Training Epoch: 2 [10496/57000]	Loss: 0.0414	LR: 0.020000
Training Epoch: 2 [10752/57000]	Loss: 0.0371	LR: 0.020000
Training Epoch: 2 [11008/57000]	Loss: 0.0967	LR: 0.020000
Training Epoch: 2 [11264/57000]	Loss: 0.0516	LR: 0.020000
Training Epoch: 2 [11520/57000]	Loss: 0.0259	LR: 0.020000
Training Epoch: 2 [11776/57000]	Loss: 0.0173	LR: 0.020000
Training Epoch: 2 [12032/57000]	Loss: 0.0196	LR: 0.020000
Training Epoch: 2 [12288/57000]	Loss: 0.0332	LR: 0.020000
Training Epoch: 2 [12544/57000]	Loss: 0.0226	LR: 0.020000
Training Epoch: 2 [12800/57000]	Loss: 0.0301	LR: 0.020000
Training Epoch: 2 [13056/57000]	Loss: 0.0317	LR: 0.020000
Training Epoch: 2 [13312/57000]	Loss: 0.0667	LR: 0.020000
Training Epoch: 2 [13568/57000]	Loss: 0.0360	LR: 0.020000
Training Epoch: 2 [13824/57000]	Loss: 0.0350	LR: 0.020000
Training Epoch: 2 [14080/57000]	Loss: 0.0286	LR: 0.020000
Training Epoch: 2 [14336/57000]	Loss: 0.0184	LR: 0.020000
Training Epoch: 2 [14592/57000]	Loss: 0.0420	LR: 0.020000
Training Epoch: 2 [14848/57000]	Loss: 0.0315	LR: 0.020000
Training Epoch: 2 [15104/57000]	Loss: 0.0500	LR: 0.020000
Training Epoch: 2 [15360/57000]	Loss: 0.0425	LR: 0.020000
Training Epoch: 2 [15616/57000]	Loss: 0.0143	LR: 0.020000
Training Epoch: 2 [15872/57000]	Loss: 0.0283	LR: 0.020000
Training Epoch: 2 [16128/57000]	Loss: 0.0444	LR: 0.020000
Training Epoch: 2 [16384/57000]	Loss: 0.0369	LR: 0.020000
Training Epoch: 2 [16640/57000]	Loss: 0.0305	LR: 0.020000
Training Epoch: 2 [16896/57000]	Loss: 0.0714	LR: 0.020000
Training Epoch: 2 [17152/57000]	Loss: 0.0250	LR: 0.020000
Training Epoch: 2 [17408/57000]	Loss: 0.0550	LR: 0.020000
Training Epoch: 2 [17664/57000]	Loss: 0.0281	LR: 0.020000
Training Epoch: 2 [17920/57000]	Loss: 0.0159	LR: 0.020000
Training Epoch: 2 [18176/57000]	Loss: 0.0249	LR: 0.020000
Training Epoch: 2 [18432/57000]	Loss: 0.0451	LR: 0.020000
Training Epoch: 2 [18688/57000]	Loss: 0.0439	LR: 0.020000
Training Epoch: 2 [18944/57000]	Loss: 0.0262	LR: 0.020000
Training Epoch: 2 [19200/57000]	Loss: 0.0591	LR: 0.020000
Training Epoch: 2 [19456/57000]	Loss: 0.0667	LR: 0.020000
Training Epoch: 2 [19712/57000]	Loss: 0.0059	LR: 0.020000
Training Epoch: 2 [19968/57000]	Loss: 0.0370	LR: 0.020000
Training Epoch: 2 [20224/57000]	Loss: 0.0670	LR: 0.020000
Training Epoch: 2 [20480/57000]	Loss: 0.0456	LR: 0.020000
Training Epoch: 2 [20736/57000]	Loss: 0.0177	LR: 0.020000
Training Epoch: 2 [20992/57000]	Loss: 0.0632	LR: 0.020000
Training Epoch: 2 [21248/57000]	Loss: 0.0387	LR: 0.020000
Training Epoch: 2 [21504/57000]	Loss: 0.0455	LR: 0.020000
Training Epoch: 2 [21760/57000]	Loss: 0.0259	LR: 0.020000
Training Epoch: 2 [22016/57000]	Loss: 0.0696	LR: 0.020000
Training Epoch: 2 [22272/57000]	Loss: 0.0284	LR: 0.020000
Training Epoch: 2 [22528/57000]	Loss: 0.0444	LR: 0.020000
Training Epoch: 2 [22784/57000]	Loss: 0.0233	LR: 0.020000
Training Epoch: 2 [23040/57000]	Loss: 0.0439	LR: 0.020000
Training Epoch: 2 [23296/57000]	Loss: 0.0482	LR: 0.020000
Training Epoch: 2 [23552/57000]	Loss: 0.0292	LR: 0.020000
Training Epoch: 2 [23808/57000]	Loss: 0.0438	LR: 0.020000
Training Epoch: 2 [24064/57000]	Loss: 0.0299	LR: 0.020000
Training Epoch: 2 [24320/57000]	Loss: 0.0371	LR: 0.020000
Training Epoch: 2 [24576/57000]	Loss: 0.0778	LR: 0.020000
Training Epoch: 2 [24832/57000]	Loss: 0.0311	LR: 0.020000
Training Epoch: 2 [25088/57000]	Loss: 0.0383	LR: 0.020000
Training Epoch: 2 [25344/57000]	Loss: 0.0587	LR: 0.020000
Training Epoch: 2 [25600/57000]	Loss: 0.0495	LR: 0.020000
Training Epoch: 2 [25856/57000]	Loss: 0.0417	LR: 0.020000
Training Epoch: 2 [26112/57000]	Loss: 0.0258	LR: 0.020000
Training Epoch: 2 [26368/57000]	Loss: 0.0307	LR: 0.020000
Training Epoch: 2 [26624/57000]	Loss: 0.0426	LR: 0.020000
Training Epoch: 2 [26880/57000]	Loss: 0.0498	LR: 0.020000
Training Epoch: 2 [27136/57000]	Loss: 0.0316	LR: 0.020000
Training Epoch: 2 [27392/57000]	Loss: 0.0634	LR: 0.020000
Training Epoch: 2 [27648/57000]	Loss: 0.0281	LR: 0.020000
Training Epoch: 2 [27904/57000]	Loss: 0.0264	LR: 0.020000
Training Epoch: 2 [28160/57000]	Loss: 0.0354	LR: 0.020000
Training Epoch: 2 [28416/57000]	Loss: 0.0493	LR: 0.020000
Training Epoch: 2 [28672/57000]	Loss: 0.0329	LR: 0.020000
Training Epoch: 2 [28928/57000]	Loss: 0.0521	LR: 0.020000
Training Epoch: 2 [29184/57000]	Loss: 0.0383	LR: 0.020000
Training Epoch: 2 [29440/57000]	Loss: 0.0262	LR: 0.020000
Training Epoch: 2 [29696/57000]	Loss: 0.0442	LR: 0.020000
Training Epoch: 2 [29952/57000]	Loss: 0.0463	LR: 0.020000
Training Epoch: 2 [30208/57000]	Loss: 0.0216	LR: 0.020000
Training Epoch: 2 [30464/57000]	Loss: 0.0482	LR: 0.020000
Training Epoch: 2 [30720/57000]	Loss: 0.0435	LR: 0.020000
Training Epoch: 2 [30976/57000]	Loss: 0.0361	LR: 0.020000
Training Epoch: 2 [31232/57000]	Loss: 0.0226	LR: 0.020000
Training Epoch: 2 [31488/57000]	Loss: 0.0588	LR: 0.020000
Training Epoch: 2 [31744/57000]	Loss: 0.0354	LR: 0.020000
Training Epoch: 2 [32000/57000]	Loss: 0.0177	LR: 0.020000
Training Epoch: 2 [32256/57000]	Loss: 0.0266	LR: 0.020000
Training Epoch: 2 [32512/57000]	Loss: 0.0529	LR: 0.020000
Training Epoch: 2 [32768/57000]	Loss: 0.0378	LR: 0.020000
Training Epoch: 2 [33024/57000]	Loss: 0.0432	LR: 0.020000
Training Epoch: 2 [33280/57000]	Loss: 0.0529	LR: 0.020000
Training Epoch: 2 [33536/57000]	Loss: 0.0319	LR: 0.020000
Training Epoch: 2 [33792/57000]	Loss: 0.0187	LR: 0.020000
Training Epoch: 2 [34048/57000]	Loss: 0.0230	LR: 0.020000
Training Epoch: 2 [34304/57000]	Loss: 0.0435	LR: 0.020000
Training Epoch: 2 [34560/57000]	Loss: 0.0157	LR: 0.020000
Training Epoch: 2 [34816/57000]	Loss: 0.0386	LR: 0.020000
Training Epoch: 2 [35072/57000]	Loss: 0.0330	LR: 0.020000
Training Epoch: 2 [35328/57000]	Loss: 0.0309	LR: 0.020000
Training Epoch: 2 [35584/57000]	Loss: 0.0409	LR: 0.020000
Training Epoch: 2 [35840/57000]	Loss: 0.0536	LR: 0.020000
Training Epoch: 2 [36096/57000]	Loss: 0.0563	LR: 0.020000
Training Epoch: 2 [36352/57000]	Loss: 0.0305	LR: 0.020000
Training Epoch: 2 [36608/57000]	Loss: 0.0158	LR: 0.020000
Training Epoch: 2 [36864/57000]	Loss: 0.0347	LR: 0.020000
Training Epoch: 2 [37120/57000]	Loss: 0.0266	LR: 0.020000
Training Epoch: 2 [37376/57000]	Loss: 0.0374	LR: 0.020000
Training Epoch: 2 [37632/57000]	Loss: 0.0171	LR: 0.020000
Training Epoch: 2 [37888/57000]	Loss: 0.0182	LR: 0.020000
Training Epoch: 2 [38144/57000]	Loss: 0.0235	LR: 0.020000
Training Epoch: 2 [38400/57000]	Loss: 0.0203	LR: 0.020000
Training Epoch: 2 [38656/57000]	Loss: 0.0193	LR: 0.020000
Training Epoch: 2 [38912/57000]	Loss: 0.0240	LR: 0.020000
Training Epoch: 2 [39168/57000]	Loss: 0.0498	LR: 0.020000
Training Epoch: 2 [39424/57000]	Loss: 0.0356	LR: 0.020000
Training Epoch: 2 [39680/57000]	Loss: 0.0275	LR: 0.020000
Training Epoch: 2 [39936/57000]	Loss: 0.0355	LR: 0.020000
Training Epoch: 2 [40192/57000]	Loss: 0.0291	LR: 0.020000
Training Epoch: 2 [40448/57000]	Loss: 0.0236	LR: 0.020000
Training Epoch: 2 [40704/57000]	Loss: 0.0218	LR: 0.020000
Training Epoch: 2 [40960/57000]	Loss: 0.0406	LR: 0.020000
Training Epoch: 2 [41216/57000]	Loss: 0.0322	LR: 0.020000
Training Epoch: 2 [41472/57000]	Loss: 0.0329	LR: 0.020000
Training Epoch: 2 [41728/57000]	Loss: 0.0491	LR: 0.020000
Training Epoch: 2 [41984/57000]	Loss: 0.0407	LR: 0.020000
Training Epoch: 2 [42240/57000]	Loss: 0.0276	LR: 0.020000
Training Epoch: 2 [42496/57000]	Loss: 0.0458	LR: 0.020000
Training Epoch: 2 [42752/57000]	Loss: 0.0203	LR: 0.020000
Training Epoch: 2 [43008/57000]	Loss: 0.0250	LR: 0.020000
Training Epoch: 2 [43264/57000]	Loss: 0.0316	LR: 0.020000
Training Epoch: 2 [43520/57000]	Loss: 0.0443	LR: 0.020000
Training Epoch: 2 [43776/57000]	Loss: 0.0422	LR: 0.020000
Training Epoch: 2 [44032/57000]	Loss: 0.0483	LR: 0.020000
Training Epoch: 2 [44288/57000]	Loss: 0.0373	LR: 0.020000
Training Epoch: 2 [44544/57000]	Loss: 0.0206	LR: 0.020000
Training Epoch: 2 [44800/57000]	Loss: 0.0162	LR: 0.020000
Training Epoch: 2 [45056/57000]	Loss: 0.0207	LR: 0.020000
Training Epoch: 2 [45312/57000]	Loss: 0.0699	LR: 0.020000
Training Epoch: 2 [45568/57000]	Loss: 0.0242	LR: 0.020000
Training Epoch: 2 [45824/57000]	Loss: 0.0468	LR: 0.020000
Training Epoch: 2 [46080/57000]	Loss: 0.0413	LR: 0.020000
Training Epoch: 2 [46336/57000]	Loss: 0.0363	LR: 0.020000
Training Epoch: 2 [46592/57000]	Loss: 0.0287	LR: 0.020000
Training Epoch: 2 [46848/57000]	Loss: 0.0508	LR: 0.020000
Training Epoch: 2 [47104/57000]	Loss: 0.0281	LR: 0.020000
Training Epoch: 2 [47360/57000]	Loss: 0.0265	LR: 0.020000
Training Epoch: 2 [47616/57000]	Loss: 0.0289	LR: 0.020000
Training Epoch: 2 [47872/57000]	Loss: 0.0412	LR: 0.020000
Training Epoch: 2 [48128/57000]	Loss: 0.0401	LR: 0.020000
Training Epoch: 2 [48384/57000]	Loss: 0.0287	LR: 0.020000
Training Epoch: 2 [48640/57000]	Loss: 0.0161	LR: 0.020000
Training Epoch: 2 [48896/57000]	Loss: 0.0396	LR: 0.020000
Training Epoch: 2 [49152/57000]	Loss: 0.0253	LR: 0.020000
Training Epoch: 2 [49408/57000]	Loss: 0.0428	LR: 0.020000
Training Epoch: 2 [49664/57000]	Loss: 0.0217	LR: 0.020000
Training Epoch: 2 [49920/57000]	Loss: 0.0173	LR: 0.020000
Training Epoch: 2 [50176/57000]	Loss: 0.0169	LR: 0.020000
Training Epoch: 2 [50432/57000]	Loss: 0.0422	LR: 0.020000
Training Epoch: 2 [50688/57000]	Loss: 0.0335	LR: 0.020000
Training Epoch: 2 [50944/57000]	Loss: 0.0592	LR: 0.020000
Training Epoch: 2 [51200/57000]	Loss: 0.0269	LR: 0.020000
Training Epoch: 2 [51456/57000]	Loss: 0.0096	LR: 0.020000
Training Epoch: 2 [51712/57000]	Loss: 0.0291	LR: 0.020000
Training Epoch: 2 [51968/57000]	Loss: 0.0553	LR: 0.020000
Training Epoch: 2 [52224/57000]	Loss: 0.0121	LR: 0.020000
Training Epoch: 2 [52480/57000]	Loss: 0.0396	LR: 0.020000
Training Epoch: 2 [52736/57000]	Loss: 0.0226	LR: 0.020000
Training Epoch: 2 [52992/57000]	Loss: 0.0301	LR: 0.020000
Training Epoch: 2 [53248/57000]	Loss: 0.0189	LR: 0.020000
Training Epoch: 2 [53504/57000]	Loss: 0.0486	LR: 0.020000
Training Epoch: 2 [53760/57000]	Loss: 0.0342	LR: 0.020000
Training Epoch: 2 [54016/57000]	Loss: 0.0217	LR: 0.020000
Training Epoch: 2 [54272/57000]	Loss: 0.0330	LR: 0.020000
Training Epoch: 2 [54528/57000]	Loss: 0.0830	LR: 0.020000
Training Epoch: 2 [54784/57000]	Loss: 0.0157	LR: 0.020000
Training Epoch: 2 [55040/57000]	Loss: 0.0436	LR: 0.020000
Training Epoch: 2 [55296/57000]	Loss: 0.0234	LR: 0.020000
Training Epoch: 2 [55552/57000]	Loss: 0.0442	LR: 0.020000
Training Epoch: 2 [55808/57000]	Loss: 0.0157	LR: 0.020000
Training Epoch: 2 [56064/57000]	Loss: 0.0159	LR: 0.020000
Training Epoch: 2 [56320/57000]	Loss: 0.0362	LR: 0.020000
Training Epoch: 2 [56576/57000]	Loss: 0.0440	LR: 0.020000
Training Epoch: 2 [56832/57000]	Loss: 0.0274	LR: 0.020000
Training Epoch: 2 [57000/57000]	Loss: 0.0389	LR: 0.020000
Epoch 2 - Average Train Loss: 0.0386, Train Accuracy: 0.9886
Epoch 2 training time consumed: 40.37s
Evaluating Network.....
Test set: Epoch: 2, Average loss: 0.0001, Accuracy: 0.9944, Time consumed:1.64s
Saving weights file to checkpoint/retrain/AllCNN/Wednesday_23_July_2025_17h_10m_19s/AllCNN-Mnist-seed8-ret50-2-best.pth
Training Epoch: 3 [256/57000]	Loss: 0.0418	LR: 0.004000
Training Epoch: 3 [512/57000]	Loss: 0.0218	LR: 0.004000
Training Epoch: 3 [768/57000]	Loss: 0.0493	LR: 0.004000
Training Epoch: 3 [1024/57000]	Loss: 0.0154	LR: 0.004000
Training Epoch: 3 [1280/57000]	Loss: 0.0254	LR: 0.004000
Training Epoch: 3 [1536/57000]	Loss: 0.0402	LR: 0.004000
Training Epoch: 3 [1792/57000]	Loss: 0.0156	LR: 0.004000
Training Epoch: 3 [2048/57000]	Loss: 0.0357	LR: 0.004000
Training Epoch: 3 [2304/57000]	Loss: 0.0129	LR: 0.004000
Training Epoch: 3 [2560/57000]	Loss: 0.0578	LR: 0.004000
Training Epoch: 3 [2816/57000]	Loss: 0.0536	LR: 0.004000
Training Epoch: 3 [3072/57000]	Loss: 0.0426	LR: 0.004000
Training Epoch: 3 [3328/57000]	Loss: 0.0139	LR: 0.004000
Training Epoch: 3 [3584/57000]	Loss: 0.0133	LR: 0.004000
Training Epoch: 3 [3840/57000]	Loss: 0.0373	LR: 0.004000
Training Epoch: 3 [4096/57000]	Loss: 0.0457	LR: 0.004000
Training Epoch: 3 [4352/57000]	Loss: 0.0263	LR: 0.004000
Training Epoch: 3 [4608/57000]	Loss: 0.0176	LR: 0.004000
Training Epoch: 3 [4864/57000]	Loss: 0.0531	LR: 0.004000
Training Epoch: 3 [5120/57000]	Loss: 0.0266	LR: 0.004000
Training Epoch: 3 [5376/57000]	Loss: 0.0247	LR: 0.004000
Training Epoch: 3 [5632/57000]	Loss: 0.0210	LR: 0.004000
Training Epoch: 3 [5888/57000]	Loss: 0.0355	LR: 0.004000
Training Epoch: 3 [6144/57000]	Loss: 0.0128	LR: 0.004000
Training Epoch: 3 [6400/57000]	Loss: 0.0153	LR: 0.004000
Training Epoch: 3 [6656/57000]	Loss: 0.0164	LR: 0.004000
Training Epoch: 3 [6912/57000]	Loss: 0.0466	LR: 0.004000
Training Epoch: 3 [7168/57000]	Loss: 0.0551	LR: 0.004000
Training Epoch: 3 [7424/57000]	Loss: 0.0178	LR: 0.004000
Training Epoch: 3 [7680/57000]	Loss: 0.0116	LR: 0.004000
Training Epoch: 3 [7936/57000]	Loss: 0.0253	LR: 0.004000
Training Epoch: 3 [8192/57000]	Loss: 0.0304	LR: 0.004000
Training Epoch: 3 [8448/57000]	Loss: 0.0489	LR: 0.004000
Training Epoch: 3 [8704/57000]	Loss: 0.0400	LR: 0.004000
Training Epoch: 3 [8960/57000]	Loss: 0.0210	LR: 0.004000
Training Epoch: 3 [9216/57000]	Loss: 0.0201	LR: 0.004000
Training Epoch: 3 [9472/57000]	Loss: 0.0465	LR: 0.004000
Training Epoch: 3 [9728/57000]	Loss: 0.0103	LR: 0.004000
Training Epoch: 3 [9984/57000]	Loss: 0.0238	LR: 0.004000
Training Epoch: 3 [10240/57000]	Loss: 0.0182	LR: 0.004000
Training Epoch: 3 [10496/57000]	Loss: 0.0208	LR: 0.004000
Training Epoch: 3 [10752/57000]	Loss: 0.0190	LR: 0.004000
Training Epoch: 3 [11008/57000]	Loss: 0.0201	LR: 0.004000
Training Epoch: 3 [11264/57000]	Loss: 0.0156	LR: 0.004000
Training Epoch: 3 [11520/57000]	Loss: 0.0338	LR: 0.004000
Training Epoch: 3 [11776/57000]	Loss: 0.0394	LR: 0.004000
Training Epoch: 3 [12032/57000]	Loss: 0.0119	LR: 0.004000
Training Epoch: 3 [12288/57000]	Loss: 0.0252	LR: 0.004000
Training Epoch: 3 [12544/57000]	Loss: 0.0282	LR: 0.004000
Training Epoch: 3 [12800/57000]	Loss: 0.0282	LR: 0.004000
Training Epoch: 3 [13056/57000]	Loss: 0.0100	LR: 0.004000
Training Epoch: 3 [13312/57000]	Loss: 0.0165	LR: 0.004000
Training Epoch: 3 [13568/57000]	Loss: 0.0078	LR: 0.004000
Training Epoch: 3 [13824/57000]	Loss: 0.0201	LR: 0.004000
Training Epoch: 3 [14080/57000]	Loss: 0.0425	LR: 0.004000
Training Epoch: 3 [14336/57000]	Loss: 0.0318	LR: 0.004000
Training Epoch: 3 [14592/57000]	Loss: 0.0100	LR: 0.004000
Training Epoch: 3 [14848/57000]	Loss: 0.0661	LR: 0.004000
Training Epoch: 3 [15104/57000]	Loss: 0.0419	LR: 0.004000
Training Epoch: 3 [15360/57000]	Loss: 0.0078	LR: 0.004000
Training Epoch: 3 [15616/57000]	Loss: 0.0274	LR: 0.004000
Training Epoch: 3 [15872/57000]	Loss: 0.0357	LR: 0.004000
Training Epoch: 3 [16128/57000]	Loss: 0.0227	LR: 0.004000
Training Epoch: 3 [16384/57000]	Loss: 0.0276	LR: 0.004000
Training Epoch: 3 [16640/57000]	Loss: 0.0163	LR: 0.004000
Training Epoch: 3 [16896/57000]	Loss: 0.0559	LR: 0.004000
Training Epoch: 3 [17152/57000]	Loss: 0.0258	LR: 0.004000
Training Epoch: 3 [17408/57000]	Loss: 0.0309	LR: 0.004000
Training Epoch: 3 [17664/57000]	Loss: 0.0224	LR: 0.004000
Training Epoch: 3 [17920/57000]	Loss: 0.0551	LR: 0.004000
Training Epoch: 3 [18176/57000]	Loss: 0.0281	LR: 0.004000
Training Epoch: 3 [18432/57000]	Loss: 0.0309	LR: 0.004000
Training Epoch: 3 [18688/57000]	Loss: 0.0230	LR: 0.004000
Training Epoch: 3 [18944/57000]	Loss: 0.0230	LR: 0.004000
Training Epoch: 3 [19200/57000]	Loss: 0.0177	LR: 0.004000
Training Epoch: 3 [19456/57000]	Loss: 0.0383	LR: 0.004000
Training Epoch: 3 [19712/57000]	Loss: 0.0609	LR: 0.004000
Training Epoch: 3 [19968/57000]	Loss: 0.0248	LR: 0.004000
Training Epoch: 3 [20224/57000]	Loss: 0.0056	LR: 0.004000
Training Epoch: 3 [20480/57000]	Loss: 0.0242	LR: 0.004000
Training Epoch: 3 [20736/57000]	Loss: 0.0195	LR: 0.004000
Training Epoch: 3 [20992/57000]	Loss: 0.0461	LR: 0.004000
Training Epoch: 3 [21248/57000]	Loss: 0.0212	LR: 0.004000
Training Epoch: 3 [21504/57000]	Loss: 0.0275	LR: 0.004000
Training Epoch: 3 [21760/57000]	Loss: 0.0308	LR: 0.004000
Training Epoch: 3 [22016/57000]	Loss: 0.0215	LR: 0.004000
Training Epoch: 3 [22272/57000]	Loss: 0.0395	LR: 0.004000
Training Epoch: 3 [22528/57000]	Loss: 0.0237	LR: 0.004000
Training Epoch: 3 [22784/57000]	Loss: 0.0328	LR: 0.004000
Training Epoch: 3 [23040/57000]	Loss: 0.0392	LR: 0.004000
Training Epoch: 3 [23296/57000]	Loss: 0.0417	LR: 0.004000
Training Epoch: 3 [23552/57000]	Loss: 0.0138	LR: 0.004000
Training Epoch: 3 [23808/57000]	Loss: 0.0200	LR: 0.004000
Training Epoch: 3 [24064/57000]	Loss: 0.0647	LR: 0.004000
Training Epoch: 3 [24320/57000]	Loss: 0.0380	LR: 0.004000
Training Epoch: 3 [24576/57000]	Loss: 0.0270	LR: 0.004000
Training Epoch: 3 [24832/57000]	Loss: 0.0305	LR: 0.004000
Training Epoch: 3 [25088/57000]	Loss: 0.0498	LR: 0.004000
Training Epoch: 3 [25344/57000]	Loss: 0.0307	LR: 0.004000
Training Epoch: 3 [25600/57000]	Loss: 0.0249	LR: 0.004000
Training Epoch: 3 [25856/57000]	Loss: 0.0378	LR: 0.004000
Training Epoch: 3 [26112/57000]	Loss: 0.0176	LR: 0.004000
Training Epoch: 3 [26368/57000]	Loss: 0.0194	LR: 0.004000
Training Epoch: 3 [26624/57000]	Loss: 0.0295	LR: 0.004000
Training Epoch: 3 [26880/57000]	Loss: 0.0209	LR: 0.004000
Training Epoch: 3 [27136/57000]	Loss: 0.0150	LR: 0.004000
Training Epoch: 3 [27392/57000]	Loss: 0.0076	LR: 0.004000
Training Epoch: 3 [27648/57000]	Loss: 0.0651	LR: 0.004000
Training Epoch: 3 [27904/57000]	Loss: 0.0237	LR: 0.004000
Training Epoch: 3 [28160/57000]	Loss: 0.0250	LR: 0.004000
Training Epoch: 3 [28416/57000]	Loss: 0.0340	LR: 0.004000
Training Epoch: 3 [28672/57000]	Loss: 0.0778	LR: 0.004000
Training Epoch: 3 [28928/57000]	Loss: 0.0221	LR: 0.004000
Training Epoch: 3 [29184/57000]	Loss: 0.0148	LR: 0.004000
Training Epoch: 3 [29440/57000]	Loss: 0.0216	LR: 0.004000
Training Epoch: 3 [29696/57000]	Loss: 0.0585	LR: 0.004000
Training Epoch: 3 [29952/57000]	Loss: 0.0443	LR: 0.004000
Training Epoch: 3 [30208/57000]	Loss: 0.0198	LR: 0.004000
Training Epoch: 3 [30464/57000]	Loss: 0.0451	LR: 0.004000
Training Epoch: 3 [30720/57000]	Loss: 0.0353	LR: 0.004000
Training Epoch: 3 [30976/57000]	Loss: 0.0218	LR: 0.004000
Training Epoch: 3 [31232/57000]	Loss: 0.0229	LR: 0.004000
Training Epoch: 3 [31488/57000]	Loss: 0.0195	LR: 0.004000
Training Epoch: 3 [31744/57000]	Loss: 0.0102	LR: 0.004000
Training Epoch: 3 [32000/57000]	Loss: 0.0255	LR: 0.004000
Training Epoch: 3 [32256/57000]	Loss: 0.0077	LR: 0.004000
Training Epoch: 3 [32512/57000]	Loss: 0.0256	LR: 0.004000
Training Epoch: 3 [32768/57000]	Loss: 0.0167	LR: 0.004000
Training Epoch: 3 [33024/57000]	Loss: 0.0232	LR: 0.004000
Training Epoch: 3 [33280/57000]	Loss: 0.0154	LR: 0.004000
Training Epoch: 3 [33536/57000]	Loss: 0.0243	LR: 0.004000
Training Epoch: 3 [33792/57000]	Loss: 0.0285	LR: 0.004000
Training Epoch: 3 [34048/57000]	Loss: 0.0244	LR: 0.004000
Training Epoch: 3 [34304/57000]	Loss: 0.0231	LR: 0.004000
Training Epoch: 3 [34560/57000]	Loss: 0.0140	LR: 0.004000
Training Epoch: 3 [34816/57000]	Loss: 0.0189	LR: 0.004000
Training Epoch: 3 [35072/57000]	Loss: 0.0099	LR: 0.004000
Training Epoch: 3 [35328/57000]	Loss: 0.0331	LR: 0.004000
Training Epoch: 3 [35584/57000]	Loss: 0.0215	LR: 0.004000
Training Epoch: 3 [35840/57000]	Loss: 0.0188	LR: 0.004000
Training Epoch: 3 [36096/57000]	Loss: 0.0116	LR: 0.004000
Training Epoch: 3 [36352/57000]	Loss: 0.0120	LR: 0.004000
Training Epoch: 3 [36608/57000]	Loss: 0.0199	LR: 0.004000
Training Epoch: 3 [36864/57000]	Loss: 0.0284	LR: 0.004000
Training Epoch: 3 [37120/57000]	Loss: 0.0129	LR: 0.004000
Training Epoch: 3 [37376/57000]	Loss: 0.0607	LR: 0.004000
Training Epoch: 3 [37632/57000]	Loss: 0.0275	LR: 0.004000
Training Epoch: 3 [37888/57000]	Loss: 0.0273	LR: 0.004000
Training Epoch: 3 [38144/57000]	Loss: 0.0116	LR: 0.004000
Training Epoch: 3 [38400/57000]	Loss: 0.0154	LR: 0.004000
Training Epoch: 3 [38656/57000]	Loss: 0.0331	LR: 0.004000
Training Epoch: 3 [38912/57000]	Loss: 0.0142	LR: 0.004000
Training Epoch: 3 [39168/57000]	Loss: 0.0351	LR: 0.004000
Training Epoch: 3 [39424/57000]	Loss: 0.0578	LR: 0.004000
Training Epoch: 3 [39680/57000]	Loss: 0.0420	LR: 0.004000
Training Epoch: 3 [39936/57000]	Loss: 0.0156	LR: 0.004000
Training Epoch: 3 [40192/57000]	Loss: 0.0194	LR: 0.004000
Training Epoch: 3 [40448/57000]	Loss: 0.0356	LR: 0.004000
Training Epoch: 3 [40704/57000]	Loss: 0.0096	LR: 0.004000
Training Epoch: 3 [40960/57000]	Loss: 0.0102	LR: 0.004000
Training Epoch: 3 [41216/57000]	Loss: 0.0269	LR: 0.004000
Training Epoch: 3 [41472/57000]	Loss: 0.0158	LR: 0.004000
Training Epoch: 3 [41728/57000]	Loss: 0.0544	LR: 0.004000
Training Epoch: 3 [41984/57000]	Loss: 0.0351	LR: 0.004000
Training Epoch: 3 [42240/57000]	Loss: 0.0338	LR: 0.004000
Training Epoch: 3 [42496/57000]	Loss: 0.0277	LR: 0.004000
Training Epoch: 3 [42752/57000]	Loss: 0.0282	LR: 0.004000
Training Epoch: 3 [43008/57000]	Loss: 0.0207	LR: 0.004000
Training Epoch: 3 [43264/57000]	Loss: 0.0178	LR: 0.004000
Training Epoch: 3 [43520/57000]	Loss: 0.0148	LR: 0.004000
Training Epoch: 3 [43776/57000]	Loss: 0.0101	LR: 0.004000
Training Epoch: 3 [44032/57000]	Loss: 0.0221	LR: 0.004000
Training Epoch: 3 [44288/57000]	Loss: 0.0273	LR: 0.004000
Training Epoch: 3 [44544/57000]	Loss: 0.0252	LR: 0.004000
Training Epoch: 3 [44800/57000]	Loss: 0.0401	LR: 0.004000
Training Epoch: 3 [45056/57000]	Loss: 0.0169	LR: 0.004000
Training Epoch: 3 [45312/57000]	Loss: 0.0213	LR: 0.004000
Training Epoch: 3 [45568/57000]	Loss: 0.0310	LR: 0.004000
Training Epoch: 3 [45824/57000]	Loss: 0.0157	LR: 0.004000
Training Epoch: 3 [46080/57000]	Loss: 0.0276	LR: 0.004000
Training Epoch: 3 [46336/57000]	Loss: 0.0106	LR: 0.004000
Training Epoch: 3 [46592/57000]	Loss: 0.0238	LR: 0.004000
Training Epoch: 3 [46848/57000]	Loss: 0.0213	LR: 0.004000
Training Epoch: 3 [47104/57000]	Loss: 0.0136	LR: 0.004000
Training Epoch: 3 [47360/57000]	Loss: 0.0149	LR: 0.004000
Training Epoch: 3 [47616/57000]	Loss: 0.0307	LR: 0.004000
Training Epoch: 3 [47872/57000]	Loss: 0.0106	LR: 0.004000
Training Epoch: 3 [48128/57000]	Loss: 0.0183	LR: 0.004000
Training Epoch: 3 [48384/57000]	Loss: 0.0160	LR: 0.004000
Training Epoch: 3 [48640/57000]	Loss: 0.0257	LR: 0.004000
Training Epoch: 3 [48896/57000]	Loss: 0.0184	LR: 0.004000
Training Epoch: 3 [49152/57000]	Loss: 0.0187	LR: 0.004000
Training Epoch: 3 [49408/57000]	Loss: 0.0215	LR: 0.004000
Training Epoch: 3 [49664/57000]	Loss: 0.0229	LR: 0.004000
Training Epoch: 3 [49920/57000]	Loss: 0.0120	LR: 0.004000
Training Epoch: 3 [50176/57000]	Loss: 0.0054	LR: 0.004000
Training Epoch: 3 [50432/57000]	Loss: 0.0193	LR: 0.004000
Training Epoch: 3 [50688/57000]	Loss: 0.0244	LR: 0.004000
Training Epoch: 3 [50944/57000]	Loss: 0.0205	LR: 0.004000
Training Epoch: 3 [51200/57000]	Loss: 0.0251	LR: 0.004000
Training Epoch: 3 [51456/57000]	Loss: 0.0285	LR: 0.004000
Training Epoch: 3 [51712/57000]	Loss: 0.0268	LR: 0.004000
Training Epoch: 3 [51968/57000]	Loss: 0.0117	LR: 0.004000
Training Epoch: 3 [52224/57000]	Loss: 0.0238	LR: 0.004000
Training Epoch: 3 [52480/57000]	Loss: 0.0102	LR: 0.004000
Training Epoch: 3 [52736/57000]	Loss: 0.0255	LR: 0.004000
Training Epoch: 3 [52992/57000]	Loss: 0.0195	LR: 0.004000
Training Epoch: 3 [53248/57000]	Loss: 0.0243	LR: 0.004000
Training Epoch: 3 [53504/57000]	Loss: 0.0230	LR: 0.004000
Training Epoch: 3 [53760/57000]	Loss: 0.0186	LR: 0.004000
Training Epoch: 3 [54016/57000]	Loss: 0.0251	LR: 0.004000
Training Epoch: 3 [54272/57000]	Loss: 0.0296	LR: 0.004000
Training Epoch: 3 [54528/57000]	Loss: 0.0244	LR: 0.004000
Training Epoch: 3 [54784/57000]	Loss: 0.0176	LR: 0.004000
Training Epoch: 3 [55040/57000]	Loss: 0.0134	LR: 0.004000
Training Epoch: 3 [55296/57000]	Loss: 0.0340	LR: 0.004000
Training Epoch: 3 [55552/57000]	Loss: 0.0102	LR: 0.004000
Training Epoch: 3 [55808/57000]	Loss: 0.0468	LR: 0.004000
Training Epoch: 3 [56064/57000]	Loss: 0.0098	LR: 0.004000
Training Epoch: 3 [56320/57000]	Loss: 0.0168	LR: 0.004000
Training Epoch: 3 [56576/57000]	Loss: 0.0332	LR: 0.004000
Training Epoch: 3 [56832/57000]	Loss: 0.0113	LR: 0.004000
Training Epoch: 3 [57000/57000]	Loss: 0.0306	LR: 0.004000
Epoch 3 - Average Train Loss: 0.0263, Train Accuracy: 0.9926
Epoch 3 training time consumed: 40.70s
Evaluating Network.....
Test set: Epoch: 3, Average loss: 0.0001, Accuracy: 0.9950, Time consumed:1.76s
Saving weights file to checkpoint/retrain/AllCNN/Wednesday_23_July_2025_17h_10m_19s/AllCNN-Mnist-seed8-ret50-3-best.pth
Training Epoch: 4 [256/57000]	Loss: 0.0224	LR: 0.000800
Training Epoch: 4 [512/57000]	Loss: 0.0099	LR: 0.000800
Training Epoch: 4 [768/57000]	Loss: 0.0222	LR: 0.000800
Training Epoch: 4 [1024/57000]	Loss: 0.0125	LR: 0.000800
Training Epoch: 4 [1280/57000]	Loss: 0.0133	LR: 0.000800
Training Epoch: 4 [1536/57000]	Loss: 0.0537	LR: 0.000800
Training Epoch: 4 [1792/57000]	Loss: 0.0151	LR: 0.000800
Training Epoch: 4 [2048/57000]	Loss: 0.0295	LR: 0.000800
Training Epoch: 4 [2304/57000]	Loss: 0.0221	LR: 0.000800
Training Epoch: 4 [2560/57000]	Loss: 0.0220	LR: 0.000800
Training Epoch: 4 [2816/57000]	Loss: 0.0187	LR: 0.000800
Training Epoch: 4 [3072/57000]	Loss: 0.0108	LR: 0.000800
Training Epoch: 4 [3328/57000]	Loss: 0.0217	LR: 0.000800
Training Epoch: 4 [3584/57000]	Loss: 0.0278	LR: 0.000800
Training Epoch: 4 [3840/57000]	Loss: 0.0272	LR: 0.000800
Training Epoch: 4 [4096/57000]	Loss: 0.0353	LR: 0.000800
Training Epoch: 4 [4352/57000]	Loss: 0.0171	LR: 0.000800
Training Epoch: 4 [4608/57000]	Loss: 0.0116	LR: 0.000800
Training Epoch: 4 [4864/57000]	Loss: 0.0261	LR: 0.000800
Training Epoch: 4 [5120/57000]	Loss: 0.0431	LR: 0.000800
Training Epoch: 4 [5376/57000]	Loss: 0.0200	LR: 0.000800
Training Epoch: 4 [5632/57000]	Loss: 0.0101	LR: 0.000800
Training Epoch: 4 [5888/57000]	Loss: 0.0099	LR: 0.000800
Training Epoch: 4 [6144/57000]	Loss: 0.0447	LR: 0.000800
Training Epoch: 4 [6400/57000]	Loss: 0.0184	LR: 0.000800
Training Epoch: 4 [6656/57000]	Loss: 0.0355	LR: 0.000800
Training Epoch: 4 [6912/57000]	Loss: 0.0373	LR: 0.000800
Training Epoch: 4 [7168/57000]	Loss: 0.0253	LR: 0.000800
Training Epoch: 4 [7424/57000]	Loss: 0.0120	LR: 0.000800
Training Epoch: 4 [7680/57000]	Loss: 0.0114	LR: 0.000800
Training Epoch: 4 [7936/57000]	Loss: 0.0295	LR: 0.000800
Training Epoch: 4 [8192/57000]	Loss: 0.0281	LR: 0.000800
Training Epoch: 4 [8448/57000]	Loss: 0.0243	LR: 0.000800
Training Epoch: 4 [8704/57000]	Loss: 0.0303	LR: 0.000800
Training Epoch: 4 [8960/57000]	Loss: 0.0253	LR: 0.000800
Training Epoch: 4 [9216/57000]	Loss: 0.0301	LR: 0.000800
Training Epoch: 4 [9472/57000]	Loss: 0.0166	LR: 0.000800
Training Epoch: 4 [9728/57000]	Loss: 0.0194	LR: 0.000800
Training Epoch: 4 [9984/57000]	Loss: 0.0317	LR: 0.000800
Training Epoch: 4 [10240/57000]	Loss: 0.0239	LR: 0.000800
Training Epoch: 4 [10496/57000]	Loss: 0.0229	LR: 0.000800
Training Epoch: 4 [10752/57000]	Loss: 0.0204	LR: 0.000800
Training Epoch: 4 [11008/57000]	Loss: 0.0183	LR: 0.000800
Training Epoch: 4 [11264/57000]	Loss: 0.0316	LR: 0.000800
Training Epoch: 4 [11520/57000]	Loss: 0.0147	LR: 0.000800
Training Epoch: 4 [11776/57000]	Loss: 0.0144	LR: 0.000800
Training Epoch: 4 [12032/57000]	Loss: 0.0220	LR: 0.000800
Training Epoch: 4 [12288/57000]	Loss: 0.0395	LR: 0.000800
Training Epoch: 4 [12544/57000]	Loss: 0.0284	LR: 0.000800
Training Epoch: 4 [12800/57000]	Loss: 0.0173	LR: 0.000800
Training Epoch: 4 [13056/57000]	Loss: 0.0202	LR: 0.000800
Training Epoch: 4 [13312/57000]	Loss: 0.0077	LR: 0.000800
Training Epoch: 4 [13568/57000]	Loss: 0.0099	LR: 0.000800
Training Epoch: 4 [13824/57000]	Loss: 0.0187	LR: 0.000800
Training Epoch: 4 [14080/57000]	Loss: 0.0390	LR: 0.000800
Training Epoch: 4 [14336/57000]	Loss: 0.0303	LR: 0.000800
Training Epoch: 4 [14592/57000]	Loss: 0.0231	LR: 0.000800
Training Epoch: 4 [14848/57000]	Loss: 0.0215	LR: 0.000800
Training Epoch: 4 [15104/57000]	Loss: 0.0123	LR: 0.000800
Training Epoch: 4 [15360/57000]	Loss: 0.0341	LR: 0.000800
Training Epoch: 4 [15616/57000]	Loss: 0.0140	LR: 0.000800
Training Epoch: 4 [15872/57000]	Loss: 0.0179	LR: 0.000800
Training Epoch: 4 [16128/57000]	Loss: 0.0217	LR: 0.000800
Training Epoch: 4 [16384/57000]	Loss: 0.0388	LR: 0.000800
Training Epoch: 4 [16640/57000]	Loss: 0.0376	LR: 0.000800
Training Epoch: 4 [16896/57000]	Loss: 0.0476	LR: 0.000800
Training Epoch: 4 [17152/57000]	Loss: 0.0265	LR: 0.000800
Training Epoch: 4 [17408/57000]	Loss: 0.0259	LR: 0.000800
Training Epoch: 4 [17664/57000]	Loss: 0.0142	LR: 0.000800
Training Epoch: 4 [17920/57000]	Loss: 0.0558	LR: 0.000800
Training Epoch: 4 [18176/57000]	Loss: 0.0174	LR: 0.000800
Training Epoch: 4 [18432/57000]	Loss: 0.0293	LR: 0.000800
Training Epoch: 4 [18688/57000]	Loss: 0.0368	LR: 0.000800
Training Epoch: 4 [18944/57000]	Loss: 0.0223	LR: 0.000800
Training Epoch: 4 [19200/57000]	Loss: 0.0298	LR: 0.000800
Training Epoch: 4 [19456/57000]	Loss: 0.0190	LR: 0.000800
Training Epoch: 4 [19712/57000]	Loss: 0.0157	LR: 0.000800
Training Epoch: 4 [19968/57000]	Loss: 0.0247	LR: 0.000800
Training Epoch: 4 [20224/57000]	Loss: 0.0275	LR: 0.000800
Training Epoch: 4 [20480/57000]	Loss: 0.0157	LR: 0.000800
Training Epoch: 4 [20736/57000]	Loss: 0.0082	LR: 0.000800
Training Epoch: 4 [20992/57000]	Loss: 0.0125	LR: 0.000800
Training Epoch: 4 [21248/57000]	Loss: 0.0113	LR: 0.000800
Training Epoch: 4 [21504/57000]	Loss: 0.0492	LR: 0.000800
Training Epoch: 4 [21760/57000]	Loss: 0.0231	LR: 0.000800
Training Epoch: 4 [22016/57000]	Loss: 0.0465	LR: 0.000800
Training Epoch: 4 [22272/57000]	Loss: 0.0104	LR: 0.000800
Training Epoch: 4 [22528/57000]	Loss: 0.0138	LR: 0.000800
Training Epoch: 4 [22784/57000]	Loss: 0.0262	LR: 0.000800
Training Epoch: 4 [23040/57000]	Loss: 0.0195	LR: 0.000800
Training Epoch: 4 [23296/57000]	Loss: 0.0160	LR: 0.000800
Training Epoch: 4 [23552/57000]	Loss: 0.0226	LR: 0.000800
Training Epoch: 4 [23808/57000]	Loss: 0.0206	LR: 0.000800
Training Epoch: 4 [24064/57000]	Loss: 0.0063	LR: 0.000800
Training Epoch: 4 [24320/57000]	Loss: 0.0308	LR: 0.000800
Training Epoch: 4 [24576/57000]	Loss: 0.0063	LR: 0.000800
Training Epoch: 4 [24832/57000]	Loss: 0.0212	LR: 0.000800
Training Epoch: 4 [25088/57000]	Loss: 0.0336	LR: 0.000800
Training Epoch: 4 [25344/57000]	Loss: 0.0206	LR: 0.000800
Training Epoch: 4 [25600/57000]	Loss: 0.0119	LR: 0.000800
Training Epoch: 4 [25856/57000]	Loss: 0.0240	LR: 0.000800
Training Epoch: 4 [26112/57000]	Loss: 0.0208	LR: 0.000800
Training Epoch: 4 [26368/57000]	Loss: 0.0205	LR: 0.000800
Training Epoch: 4 [26624/57000]	Loss: 0.0499	LR: 0.000800
Training Epoch: 4 [26880/57000]	Loss: 0.0077	LR: 0.000800
Training Epoch: 4 [27136/57000]	Loss: 0.0450	LR: 0.000800
Training Epoch: 4 [27392/57000]	Loss: 0.0197	LR: 0.000800
Training Epoch: 4 [27648/57000]	Loss: 0.0182	LR: 0.000800
Training Epoch: 4 [27904/57000]	Loss: 0.0172	LR: 0.000800
Training Epoch: 4 [28160/57000]	Loss: 0.0096	LR: 0.000800
Training Epoch: 4 [28416/57000]	Loss: 0.0265	LR: 0.000800
Training Epoch: 4 [28672/57000]	Loss: 0.0082	LR: 0.000800
Training Epoch: 4 [28928/57000]	Loss: 0.0292	LR: 0.000800
Training Epoch: 4 [29184/57000]	Loss: 0.0544	LR: 0.000800
Training Epoch: 4 [29440/57000]	Loss: 0.0251	LR: 0.000800
Training Epoch: 4 [29696/57000]	Loss: 0.0144	LR: 0.000800
Training Epoch: 4 [29952/57000]	Loss: 0.0360	LR: 0.000800
Training Epoch: 4 [30208/57000]	Loss: 0.0329	LR: 0.000800
Training Epoch: 4 [30464/57000]	Loss: 0.0107	LR: 0.000800
Training Epoch: 4 [30720/57000]	Loss: 0.0090	LR: 0.000800
Training Epoch: 4 [30976/57000]	Loss: 0.0093	LR: 0.000800
Training Epoch: 4 [31232/57000]	Loss: 0.0141	LR: 0.000800
Training Epoch: 4 [31488/57000]	Loss: 0.0115	LR: 0.000800
Training Epoch: 4 [31744/57000]	Loss: 0.0192	LR: 0.000800
Training Epoch: 4 [32000/57000]	Loss: 0.0299	LR: 0.000800
Training Epoch: 4 [32256/57000]	Loss: 0.0154	LR: 0.000800
Training Epoch: 4 [32512/57000]	Loss: 0.0288	LR: 0.000800
Training Epoch: 4 [32768/57000]	Loss: 0.0471	LR: 0.000800
Training Epoch: 4 [33024/57000]	Loss: 0.0200	LR: 0.000800
Training Epoch: 4 [33280/57000]	Loss: 0.0350	LR: 0.000800
Training Epoch: 4 [33536/57000]	Loss: 0.0290	LR: 0.000800
Training Epoch: 4 [33792/57000]	Loss: 0.0129	LR: 0.000800
Training Epoch: 4 [34048/57000]	Loss: 0.0138	LR: 0.000800
Training Epoch: 4 [34304/57000]	Loss: 0.0134	LR: 0.000800
Training Epoch: 4 [34560/57000]	Loss: 0.0144	LR: 0.000800
Training Epoch: 4 [34816/57000]	Loss: 0.0234	LR: 0.000800
Training Epoch: 4 [35072/57000]	Loss: 0.0441	LR: 0.000800
Training Epoch: 4 [35328/57000]	Loss: 0.0201	LR: 0.000800
Training Epoch: 4 [35584/57000]	Loss: 0.0152	LR: 0.000800
Training Epoch: 4 [35840/57000]	Loss: 0.0089	LR: 0.000800
Training Epoch: 4 [36096/57000]	Loss: 0.0248	LR: 0.000800
Training Epoch: 4 [36352/57000]	Loss: 0.0173	LR: 0.000800
Training Epoch: 4 [36608/57000]	Loss: 0.0145	LR: 0.000800
Training Epoch: 4 [36864/57000]	Loss: 0.0379	LR: 0.000800
Training Epoch: 4 [37120/57000]	Loss: 0.0260	LR: 0.000800
Training Epoch: 4 [37376/57000]	Loss: 0.0052	LR: 0.000800
Training Epoch: 4 [37632/57000]	Loss: 0.0281	LR: 0.000800
Training Epoch: 4 [37888/57000]	Loss: 0.0080	LR: 0.000800
Training Epoch: 4 [38144/57000]	Loss: 0.0200	LR: 0.000800
Training Epoch: 4 [38400/57000]	Loss: 0.0228	LR: 0.000800
Training Epoch: 4 [38656/57000]	Loss: 0.0357	LR: 0.000800
Training Epoch: 4 [38912/57000]	Loss: 0.0109	LR: 0.000800
Training Epoch: 4 [39168/57000]	Loss: 0.0268	LR: 0.000800
Training Epoch: 4 [39424/57000]	Loss: 0.0131	LR: 0.000800
Training Epoch: 4 [39680/57000]	Loss: 0.0494	LR: 0.000800
Training Epoch: 4 [39936/57000]	Loss: 0.0257	LR: 0.000800
Training Epoch: 4 [40192/57000]	Loss: 0.0214	LR: 0.000800
Training Epoch: 4 [40448/57000]	Loss: 0.0206	LR: 0.000800
Training Epoch: 4 [40704/57000]	Loss: 0.0241	LR: 0.000800
Training Epoch: 4 [40960/57000]	Loss: 0.0216	LR: 0.000800
Training Epoch: 4 [41216/57000]	Loss: 0.0211	LR: 0.000800
Training Epoch: 4 [41472/57000]	Loss: 0.0076	LR: 0.000800
Training Epoch: 4 [41728/57000]	Loss: 0.0321	LR: 0.000800
Training Epoch: 4 [41984/57000]	Loss: 0.0140	LR: 0.000800
Training Epoch: 4 [42240/57000]	Loss: 0.0187	LR: 0.000800
Training Epoch: 4 [42496/57000]	Loss: 0.0430	LR: 0.000800
Training Epoch: 4 [42752/57000]	Loss: 0.0218	LR: 0.000800
Training Epoch: 4 [43008/57000]	Loss: 0.0222	LR: 0.000800
Training Epoch: 4 [43264/57000]	Loss: 0.0086	LR: 0.000800
Training Epoch: 4 [43520/57000]	Loss: 0.0227	LR: 0.000800
Training Epoch: 4 [43776/57000]	Loss: 0.0284	LR: 0.000800
Training Epoch: 4 [44032/57000]	Loss: 0.0238	LR: 0.000800
Training Epoch: 4 [44288/57000]	Loss: 0.0541	LR: 0.000800
Training Epoch: 4 [44544/57000]	Loss: 0.0160	LR: 0.000800
Training Epoch: 4 [44800/57000]	Loss: 0.0227	LR: 0.000800
Training Epoch: 4 [45056/57000]	Loss: 0.0422	LR: 0.000800
Training Epoch: 4 [45312/57000]	Loss: 0.0289	LR: 0.000800
Training Epoch: 4 [45568/57000]	Loss: 0.0241	LR: 0.000800
Training Epoch: 4 [45824/57000]	Loss: 0.0138	LR: 0.000800
Training Epoch: 4 [46080/57000]	Loss: 0.0184	LR: 0.000800
Training Epoch: 4 [46336/57000]	Loss: 0.0145	LR: 0.000800
Training Epoch: 4 [46592/57000]	Loss: 0.0145	LR: 0.000800
Training Epoch: 4 [46848/57000]	Loss: 0.0120	LR: 0.000800
Training Epoch: 4 [47104/57000]	Loss: 0.0187	LR: 0.000800
Training Epoch: 4 [47360/57000]	Loss: 0.0197	LR: 0.000800
Training Epoch: 4 [47616/57000]	Loss: 0.0140	LR: 0.000800
Training Epoch: 4 [47872/57000]	Loss: 0.0127	LR: 0.000800
Training Epoch: 4 [48128/57000]	Loss: 0.0099	LR: 0.000800
Training Epoch: 4 [48384/57000]	Loss: 0.0154	LR: 0.000800
Training Epoch: 4 [48640/57000]	Loss: 0.0317	LR: 0.000800
Training Epoch: 4 [48896/57000]	Loss: 0.0078	LR: 0.000800
Training Epoch: 4 [49152/57000]	Loss: 0.0155	LR: 0.000800
Training Epoch: 4 [49408/57000]	Loss: 0.0162	LR: 0.000800
Training Epoch: 4 [49664/57000]	Loss: 0.0537	LR: 0.000800
Training Epoch: 4 [49920/57000]	Loss: 0.0260	LR: 0.000800
Training Epoch: 4 [50176/57000]	Loss: 0.0063	LR: 0.000800
Training Epoch: 4 [50432/57000]	Loss: 0.0230	LR: 0.000800
Training Epoch: 4 [50688/57000]	Loss: 0.0254	LR: 0.000800
Training Epoch: 4 [50944/57000]	Loss: 0.0214	LR: 0.000800
Training Epoch: 4 [51200/57000]	Loss: 0.0457	LR: 0.000800
Training Epoch: 4 [51456/57000]	Loss: 0.0164	LR: 0.000800
Training Epoch: 4 [51712/57000]	Loss: 0.0312	LR: 0.000800
Training Epoch: 4 [51968/57000]	Loss: 0.0308	LR: 0.000800
Training Epoch: 4 [52224/57000]	Loss: 0.0608	LR: 0.000800
Training Epoch: 4 [52480/57000]	Loss: 0.0879	LR: 0.000800
Training Epoch: 4 [52736/57000]	Loss: 0.0415	LR: 0.000800
Training Epoch: 4 [52992/57000]	Loss: 0.0304	LR: 0.000800
Training Epoch: 4 [53248/57000]	Loss: 0.0329	LR: 0.000800
Training Epoch: 4 [53504/57000]	Loss: 0.0307	LR: 0.000800
Training Epoch: 4 [53760/57000]	Loss: 0.0169	LR: 0.000800
Training Epoch: 4 [54016/57000]	Loss: 0.0151	LR: 0.000800
Training Epoch: 4 [54272/57000]	Loss: 0.0125	LR: 0.000800
Training Epoch: 4 [54528/57000]	Loss: 0.0174	LR: 0.000800
Training Epoch: 4 [54784/57000]	Loss: 0.0097	LR: 0.000800
Training Epoch: 4 [55040/57000]	Loss: 0.0127	LR: 0.000800
Training Epoch: 4 [55296/57000]	Loss: 0.0749	LR: 0.000800
Training Epoch: 4 [55552/57000]	Loss: 0.0161	LR: 0.000800
Training Epoch: 4 [55808/57000]	Loss: 0.0074	LR: 0.000800
Training Epoch: 4 [56064/57000]	Loss: 0.0274	LR: 0.000800
Training Epoch: 4 [56320/57000]	Loss: 0.0120	LR: 0.000800
Training Epoch: 4 [56576/57000]	Loss: 0.0277	LR: 0.000800
Training Epoch: 4 [56832/57000]	Loss: 0.0294	LR: 0.000800
Training Epoch: 4 [57000/57000]	Loss: 0.0200	LR: 0.000800
Epoch 4 - Average Train Loss: 0.0235, Train Accuracy: 0.9940
Epoch 4 training time consumed: 40.55s
Evaluating Network.....
Test set: Epoch: 4, Average loss: 0.0001, Accuracy: 0.9952, Time consumed:1.72s
Saving weights file to checkpoint/retrain/AllCNN/Wednesday_23_July_2025_17h_10m_19s/AllCNN-Mnist-seed8-ret50-4-best.pth
Training Epoch: 5 [256/57000]	Loss: 0.0190	LR: 0.000800
Training Epoch: 5 [512/57000]	Loss: 0.0273	LR: 0.000800
Training Epoch: 5 [768/57000]	Loss: 0.0142	LR: 0.000800
Training Epoch: 5 [1024/57000]	Loss: 0.0322	LR: 0.000800
Training Epoch: 5 [1280/57000]	Loss: 0.0369	LR: 0.000800
Training Epoch: 5 [1536/57000]	Loss: 0.0153	LR: 0.000800
Training Epoch: 5 [1792/57000]	Loss: 0.0244	LR: 0.000800
Training Epoch: 5 [2048/57000]	Loss: 0.0360	LR: 0.000800
Training Epoch: 5 [2304/57000]	Loss: 0.0439	LR: 0.000800
Training Epoch: 5 [2560/57000]	Loss: 0.0639	LR: 0.000800
Training Epoch: 5 [2816/57000]	Loss: 0.0282	LR: 0.000800
Training Epoch: 5 [3072/57000]	Loss: 0.0180	LR: 0.000800
Training Epoch: 5 [3328/57000]	Loss: 0.0238	LR: 0.000800
Training Epoch: 5 [3584/57000]	Loss: 0.0410	LR: 0.000800
Training Epoch: 5 [3840/57000]	Loss: 0.0306	LR: 0.000800
Training Epoch: 5 [4096/57000]	Loss: 0.0117	LR: 0.000800
Training Epoch: 5 [4352/57000]	Loss: 0.0124	LR: 0.000800
Training Epoch: 5 [4608/57000]	Loss: 0.0252	LR: 0.000800
Training Epoch: 5 [4864/57000]	Loss: 0.0163	LR: 0.000800
Training Epoch: 5 [5120/57000]	Loss: 0.0297	LR: 0.000800
Training Epoch: 5 [5376/57000]	Loss: 0.0318	LR: 0.000800
Training Epoch: 5 [5632/57000]	Loss: 0.0320	LR: 0.000800
Training Epoch: 5 [5888/57000]	Loss: 0.0148	LR: 0.000800
Training Epoch: 5 [6144/57000]	Loss: 0.0109	LR: 0.000800
Training Epoch: 5 [6400/57000]	Loss: 0.0193	LR: 0.000800
Training Epoch: 5 [6656/57000]	Loss: 0.0229	LR: 0.000800
Training Epoch: 5 [6912/57000]	Loss: 0.0178	LR: 0.000800
Training Epoch: 5 [7168/57000]	Loss: 0.0140	LR: 0.000800
Training Epoch: 5 [7424/57000]	Loss: 0.0337	LR: 0.000800
Training Epoch: 5 [7680/57000]	Loss: 0.0314	LR: 0.000800
Training Epoch: 5 [7936/57000]	Loss: 0.0109	LR: 0.000800
Training Epoch: 5 [8192/57000]	Loss: 0.0113	LR: 0.000800
Training Epoch: 5 [8448/57000]	Loss: 0.0414	LR: 0.000800
Training Epoch: 5 [8704/57000]	Loss: 0.0108	LR: 0.000800
Training Epoch: 5 [8960/57000]	Loss: 0.0094	LR: 0.000800
Training Epoch: 5 [9216/57000]	Loss: 0.0237	LR: 0.000800
Training Epoch: 5 [9472/57000]	Loss: 0.0125	LR: 0.000800
Training Epoch: 5 [9728/57000]	Loss: 0.0091	LR: 0.000800
Training Epoch: 5 [9984/57000]	Loss: 0.0403	LR: 0.000800
Training Epoch: 5 [10240/57000]	Loss: 0.0269	LR: 0.000800
Training Epoch: 5 [10496/57000]	Loss: 0.0122	LR: 0.000800
Training Epoch: 5 [10752/57000]	Loss: 0.0226	LR: 0.000800
Training Epoch: 5 [11008/57000]	Loss: 0.0196	LR: 0.000800
Training Epoch: 5 [11264/57000]	Loss: 0.0143	LR: 0.000800
Training Epoch: 5 [11520/57000]	Loss: 0.0213	LR: 0.000800
Training Epoch: 5 [11776/57000]	Loss: 0.0144	LR: 0.000800
Training Epoch: 5 [12032/57000]	Loss: 0.0398	LR: 0.000800
Training Epoch: 5 [12288/57000]	Loss: 0.0118	LR: 0.000800
Training Epoch: 5 [12544/57000]	Loss: 0.0200	LR: 0.000800
Training Epoch: 5 [12800/57000]	Loss: 0.0285	LR: 0.000800
Training Epoch: 5 [13056/57000]	Loss: 0.0107	LR: 0.000800
Training Epoch: 5 [13312/57000]	Loss: 0.0089	LR: 0.000800
Training Epoch: 5 [13568/57000]	Loss: 0.0152	LR: 0.000800
Training Epoch: 5 [13824/57000]	Loss: 0.0124	LR: 0.000800
Training Epoch: 5 [14080/57000]	Loss: 0.0125	LR: 0.000800
Training Epoch: 5 [14336/57000]	Loss: 0.0215	LR: 0.000800
Training Epoch: 5 [14592/57000]	Loss: 0.0325	LR: 0.000800
Training Epoch: 5 [14848/57000]	Loss: 0.0162	LR: 0.000800
Training Epoch: 5 [15104/57000]	Loss: 0.0243	LR: 0.000800
Training Epoch: 5 [15360/57000]	Loss: 0.0184	LR: 0.000800
Training Epoch: 5 [15616/57000]	Loss: 0.0349	LR: 0.000800
Training Epoch: 5 [15872/57000]	Loss: 0.0250	LR: 0.000800
Training Epoch: 5 [16128/57000]	Loss: 0.0415	LR: 0.000800
Training Epoch: 5 [16384/57000]	Loss: 0.0299	LR: 0.000800
Training Epoch: 5 [16640/57000]	Loss: 0.0349	LR: 0.000800
Training Epoch: 5 [16896/57000]	Loss: 0.0209	LR: 0.000800
Training Epoch: 5 [17152/57000]	Loss: 0.0102	LR: 0.000800
Training Epoch: 5 [17408/57000]	Loss: 0.0314	LR: 0.000800
Training Epoch: 5 [17664/57000]	Loss: 0.0132	LR: 0.000800
Training Epoch: 5 [17920/57000]	Loss: 0.0218	LR: 0.000800
Training Epoch: 5 [18176/57000]	Loss: 0.0177	LR: 0.000800
Training Epoch: 5 [18432/57000]	Loss: 0.0224	LR: 0.000800
Training Epoch: 5 [18688/57000]	Loss: 0.0420	LR: 0.000800
Training Epoch: 5 [18944/57000]	Loss: 0.0398	LR: 0.000800
Training Epoch: 5 [19200/57000]	Loss: 0.0243	LR: 0.000800
Training Epoch: 5 [19456/57000]	Loss: 0.0440	LR: 0.000800
Training Epoch: 5 [19712/57000]	Loss: 0.0246	LR: 0.000800
Training Epoch: 5 [19968/57000]	Loss: 0.0188	LR: 0.000800
Training Epoch: 5 [20224/57000]	Loss: 0.0218	LR: 0.000800
Training Epoch: 5 [20480/57000]	Loss: 0.0389	LR: 0.000800
Training Epoch: 5 [20736/57000]	Loss: 0.0119	LR: 0.000800
Training Epoch: 5 [20992/57000]	Loss: 0.0189	LR: 0.000800
Training Epoch: 5 [21248/57000]	Loss: 0.0216	LR: 0.000800
Training Epoch: 5 [21504/57000]	Loss: 0.0333	LR: 0.000800
Training Epoch: 5 [21760/57000]	Loss: 0.0317	LR: 0.000800
Training Epoch: 5 [22016/57000]	Loss: 0.0268	LR: 0.000800
Training Epoch: 5 [22272/57000]	Loss: 0.0403	LR: 0.000800
Training Epoch: 5 [22528/57000]	Loss: 0.0138	LR: 0.000800
Training Epoch: 5 [22784/57000]	Loss: 0.0270	LR: 0.000800
Training Epoch: 5 [23040/57000]	Loss: 0.0169	LR: 0.000800
Training Epoch: 5 [23296/57000]	Loss: 0.0306	LR: 0.000800
Training Epoch: 5 [23552/57000]	Loss: 0.0309	LR: 0.000800
Training Epoch: 5 [23808/57000]	Loss: 0.0240	LR: 0.000800
Training Epoch: 5 [24064/57000]	Loss: 0.0423	LR: 0.000800
Training Epoch: 5 [24320/57000]	Loss: 0.0214	LR: 0.000800
Training Epoch: 5 [24576/57000]	Loss: 0.0252	LR: 0.000800
Training Epoch: 5 [24832/57000]	Loss: 0.0238	LR: 0.000800
Training Epoch: 5 [25088/57000]	Loss: 0.0557	LR: 0.000800
Training Epoch: 5 [25344/57000]	Loss: 0.0088	LR: 0.000800
Training Epoch: 5 [25600/57000]	Loss: 0.0251	LR: 0.000800
Training Epoch: 5 [25856/57000]	Loss: 0.0114	LR: 0.000800
Training Epoch: 5 [26112/57000]	Loss: 0.0156	LR: 0.000800
Training Epoch: 5 [26368/57000]	Loss: 0.0100	LR: 0.000800
Training Epoch: 5 [26624/57000]	Loss: 0.0150	LR: 0.000800
Training Epoch: 5 [26880/57000]	Loss: 0.0272	LR: 0.000800
Training Epoch: 5 [27136/57000]	Loss: 0.0343	LR: 0.000800
Training Epoch: 5 [27392/57000]	Loss: 0.0164	LR: 0.000800
Training Epoch: 5 [27648/57000]	Loss: 0.0111	LR: 0.000800
Training Epoch: 5 [27904/57000]	Loss: 0.0197	LR: 0.000800
Training Epoch: 5 [28160/57000]	Loss: 0.0123	LR: 0.000800
Training Epoch: 5 [28416/57000]	Loss: 0.0161	LR: 0.000800
Training Epoch: 5 [28672/57000]	Loss: 0.0210	LR: 0.000800
Training Epoch: 5 [28928/57000]	Loss: 0.0362	LR: 0.000800
Training Epoch: 5 [29184/57000]	Loss: 0.0436	LR: 0.000800
Training Epoch: 5 [29440/57000]	Loss: 0.0656	LR: 0.000800
Training Epoch: 5 [29696/57000]	Loss: 0.0187	LR: 0.000800
Training Epoch: 5 [29952/57000]	Loss: 0.0143	LR: 0.000800
Training Epoch: 5 [30208/57000]	Loss: 0.0269	LR: 0.000800
Training Epoch: 5 [30464/57000]	Loss: 0.0103	LR: 0.000800
Training Epoch: 5 [30720/57000]	Loss: 0.0167	LR: 0.000800
Training Epoch: 5 [30976/57000]	Loss: 0.0248	LR: 0.000800
Training Epoch: 5 [31232/57000]	Loss: 0.0307	LR: 0.000800
Training Epoch: 5 [31488/57000]	Loss: 0.0105	LR: 0.000800
Training Epoch: 5 [31744/57000]	Loss: 0.0310	LR: 0.000800
Training Epoch: 5 [32000/57000]	Loss: 0.0209	LR: 0.000800
Training Epoch: 5 [32256/57000]	Loss: 0.0258	LR: 0.000800
Training Epoch: 5 [32512/57000]	Loss: 0.0277	LR: 0.000800
Training Epoch: 5 [32768/57000]	Loss: 0.0287	LR: 0.000800
Training Epoch: 5 [33024/57000]	Loss: 0.0303	LR: 0.000800
Training Epoch: 5 [33280/57000]	Loss: 0.0201	LR: 0.000800
Training Epoch: 5 [33536/57000]	Loss: 0.0298	LR: 0.000800
Training Epoch: 5 [33792/57000]	Loss: 0.0252	LR: 0.000800
Training Epoch: 5 [34048/57000]	Loss: 0.0161	LR: 0.000800
Training Epoch: 5 [34304/57000]	Loss: 0.0359	LR: 0.000800
Training Epoch: 5 [34560/57000]	Loss: 0.0456	LR: 0.000800
Training Epoch: 5 [34816/57000]	Loss: 0.0095	LR: 0.000800
Training Epoch: 5 [35072/57000]	Loss: 0.0129	LR: 0.000800
Training Epoch: 5 [35328/57000]	Loss: 0.0274	LR: 0.000800
Training Epoch: 5 [35584/57000]	Loss: 0.0187	LR: 0.000800
Training Epoch: 5 [35840/57000]	Loss: 0.0306	LR: 0.000800
Training Epoch: 5 [36096/57000]	Loss: 0.0183	LR: 0.000800
Training Epoch: 5 [36352/57000]	Loss: 0.0448	LR: 0.000800
Training Epoch: 5 [36608/57000]	Loss: 0.0139	LR: 0.000800
Training Epoch: 5 [36864/57000]	Loss: 0.0218	LR: 0.000800
Training Epoch: 5 [37120/57000]	Loss: 0.0185	LR: 0.000800
Training Epoch: 5 [37376/57000]	Loss: 0.0063	LR: 0.000800
Training Epoch: 5 [37632/57000]	Loss: 0.0220	LR: 0.000800
Training Epoch: 5 [37888/57000]	Loss: 0.0466	LR: 0.000800
Training Epoch: 5 [38144/57000]	Loss: 0.0516	LR: 0.000800
Training Epoch: 5 [38400/57000]	Loss: 0.0058	LR: 0.000800
Training Epoch: 5 [38656/57000]	Loss: 0.0081	LR: 0.000800
Training Epoch: 5 [38912/57000]	Loss: 0.0205	LR: 0.000800
Training Epoch: 5 [39168/57000]	Loss: 0.0316	LR: 0.000800
Training Epoch: 5 [39424/57000]	Loss: 0.0113	LR: 0.000800
Training Epoch: 5 [39680/57000]	Loss: 0.0121	LR: 0.000800
Training Epoch: 5 [39936/57000]	Loss: 0.0194	LR: 0.000800
Training Epoch: 5 [40192/57000]	Loss: 0.0230	LR: 0.000800
Training Epoch: 5 [40448/57000]	Loss: 0.0266	LR: 0.000800
Training Epoch: 5 [40704/57000]	Loss: 0.0226	LR: 0.000800
Training Epoch: 5 [40960/57000]	Loss: 0.0183	LR: 0.000800
Training Epoch: 5 [41216/57000]	Loss: 0.0452	LR: 0.000800
Training Epoch: 5 [41472/57000]	Loss: 0.0097	LR: 0.000800
Training Epoch: 5 [41728/57000]	Loss: 0.0304	LR: 0.000800
Training Epoch: 5 [41984/57000]	Loss: 0.0184	LR: 0.000800
Training Epoch: 5 [42240/57000]	Loss: 0.0244	LR: 0.000800
Training Epoch: 5 [42496/57000]	Loss: 0.0352	LR: 0.000800
Training Epoch: 5 [42752/57000]	Loss: 0.0231	LR: 0.000800
Training Epoch: 5 [43008/57000]	Loss: 0.0287	LR: 0.000800
Training Epoch: 5 [43264/57000]	Loss: 0.0336	LR: 0.000800
Training Epoch: 5 [43520/57000]	Loss: 0.0318	LR: 0.000800
Training Epoch: 5 [43776/57000]	Loss: 0.0228	LR: 0.000800
Training Epoch: 5 [44032/57000]	Loss: 0.0275	LR: 0.000800
Training Epoch: 5 [44288/57000]	Loss: 0.0097	LR: 0.000800
Training Epoch: 5 [44544/57000]	Loss: 0.0226	LR: 0.000800
Training Epoch: 5 [44800/57000]	Loss: 0.0115	LR: 0.000800
Training Epoch: 5 [45056/57000]	Loss: 0.0237	LR: 0.000800
Training Epoch: 5 [45312/57000]	Loss: 0.0336	LR: 0.000800
Training Epoch: 5 [45568/57000]	Loss: 0.0264	LR: 0.000800
Training Epoch: 5 [45824/57000]	Loss: 0.0277	LR: 0.000800
Training Epoch: 5 [46080/57000]	Loss: 0.0107	LR: 0.000800
Training Epoch: 5 [46336/57000]	Loss: 0.0326	LR: 0.000800
Training Epoch: 5 [46592/57000]	Loss: 0.0167	LR: 0.000800
Training Epoch: 5 [46848/57000]	Loss: 0.0188	LR: 0.000800
Training Epoch: 5 [47104/57000]	Loss: 0.0295	LR: 0.000800
Training Epoch: 5 [47360/57000]	Loss: 0.0135	LR: 0.000800
Training Epoch: 5 [47616/57000]	Loss: 0.0116	LR: 0.000800
Training Epoch: 5 [47872/57000]	Loss: 0.0260	LR: 0.000800
Training Epoch: 5 [48128/57000]	Loss: 0.0195	LR: 0.000800
Training Epoch: 5 [48384/57000]	Loss: 0.0150	LR: 0.000800
Training Epoch: 5 [48640/57000]	Loss: 0.0174	LR: 0.000800
Training Epoch: 5 [48896/57000]	Loss: 0.0141	LR: 0.000800
Training Epoch: 5 [49152/57000]	Loss: 0.0183	LR: 0.000800
Training Epoch: 5 [49408/57000]	Loss: 0.0215	LR: 0.000800
Training Epoch: 5 [49664/57000]	Loss: 0.0128	LR: 0.000800
Training Epoch: 5 [49920/57000]	Loss: 0.0141	LR: 0.000800
Training Epoch: 5 [50176/57000]	Loss: 0.0134	LR: 0.000800
Training Epoch: 5 [50432/57000]	Loss: 0.0398	LR: 0.000800
Training Epoch: 5 [50688/57000]	Loss: 0.0237	LR: 0.000800
Training Epoch: 5 [50944/57000]	Loss: 0.0089	LR: 0.000800
Training Epoch: 5 [51200/57000]	Loss: 0.0091	LR: 0.000800
Training Epoch: 5 [51456/57000]	Loss: 0.0198	LR: 0.000800
Training Epoch: 5 [51712/57000]	Loss: 0.0162	LR: 0.000800
Training Epoch: 5 [51968/57000]	Loss: 0.0104	LR: 0.000800
Training Epoch: 5 [52224/57000]	Loss: 0.0187	LR: 0.000800
Training Epoch: 5 [52480/57000]	Loss: 0.0086	LR: 0.000800
Training Epoch: 5 [52736/57000]	Loss: 0.0296	LR: 0.000800
Training Epoch: 5 [52992/57000]	Loss: 0.0214	LR: 0.000800
Training Epoch: 5 [53248/57000]	Loss: 0.0082	LR: 0.000800
Training Epoch: 5 [53504/57000]	Loss: 0.0233	LR: 0.000800
Training Epoch: 5 [53760/57000]	Loss: 0.0205	LR: 0.000800
Training Epoch: 5 [54016/57000]	Loss: 0.0297	LR: 0.000800
Training Epoch: 5 [54272/57000]	Loss: 0.0269	LR: 0.000800
Training Epoch: 5 [54528/57000]	Loss: 0.0264	LR: 0.000800
Training Epoch: 5 [54784/57000]	Loss: 0.0077	LR: 0.000800
Training Epoch: 5 [55040/57000]	Loss: 0.0262	LR: 0.000800
Training Epoch: 5 [55296/57000]	Loss: 0.0324	LR: 0.000800
Training Epoch: 5 [55552/57000]	Loss: 0.0324	LR: 0.000800
Training Epoch: 5 [55808/57000]	Loss: 0.0151	LR: 0.000800
Training Epoch: 5 [56064/57000]	Loss: 0.0209	LR: 0.000800
Training Epoch: 5 [56320/57000]	Loss: 0.0106	LR: 0.000800
Training Epoch: 5 [56576/57000]	Loss: 0.0306	LR: 0.000800
Training Epoch: 5 [56832/57000]	Loss: 0.0154	LR: 0.000800
Training Epoch: 5 [57000/57000]	Loss: 0.0139	LR: 0.000800
Epoch 5 - Average Train Loss: 0.0232, Train Accuracy: 0.9936
Epoch 5 training time consumed: 40.45s
Evaluating Network.....
Test set: Epoch: 5, Average loss: 0.0001, Accuracy: 0.9949, Time consumed:1.70s
Valid (Test) Dl:  10000
Train Dl:  60000
Retain Train Dl:  57000
Forget Train Dl:  3000
Retain Valid Dl:  57000
Forget Valid Dl:  3000
retain_prob Distribution: 10000 samples
test_prob Distribution: 10000 samples
forget_prob Distribution: 3000 samples
Set1 Distribution: 3000 samples
Set2 Distribution: 3000 samples
Set1 Distribution: 3000 samples
Set2 Distribution: 3000 samples
Set1 Distribution: 10000 samples
Set2 Distribution: 10000 samples
Set1 Distribution: 10000 samples
Set2 Distribution: 10000 samples
Test Accuracy: 99.501953125
Retain Accuracy: 99.46306610107422
Zero-Retain Forget (ZRF): 0.7971183061599731
Membership Inference Attack (MIA): 0.8173333333333334
Forget vs Retain Membership Inference Attack (MIA): 0.52
Forget vs Test Membership Inference Attack (MIA): 0.5066666666666667
Test vs Retain Membership Inference Attack (MIA): 0.52425
Train vs Test Membership Inference Attack (MIA): 0.49975
Forget Set Accuracy (Df): 99.225830078125
Method Execution Time: 858.68 seconds
