
📌S Retain class distribution for seed 1:
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 1:
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
79
⚠️ Warning: Retain train loader may not be shuffled.
Training Epoch: 1 [256/54000]	Loss: 2.3596	LR: 0.000000
Training Epoch: 1 [512/54000]	Loss: 2.3570	LR: 0.000474
Training Epoch: 1 [768/54000]	Loss: 2.3214	LR: 0.000948
Training Epoch: 1 [1024/54000]	Loss: 2.3138	LR: 0.001422
Training Epoch: 1 [1280/54000]	Loss: 2.3423	LR: 0.001896
Training Epoch: 1 [1536/54000]	Loss: 2.3179	LR: 0.002370
Training Epoch: 1 [1792/54000]	Loss: 2.2995	LR: 0.002844
Training Epoch: 1 [2048/54000]	Loss: 2.3035	LR: 0.003318
Training Epoch: 1 [2304/54000]	Loss: 2.2910	LR: 0.003791
Training Epoch: 1 [2560/54000]	Loss: 2.2497	LR: 0.004265
Training Epoch: 1 [2816/54000]	Loss: 2.2300	LR: 0.004739
Training Epoch: 1 [3072/54000]	Loss: 2.2166	LR: 0.005213
Training Epoch: 1 [3328/54000]	Loss: 2.2180	LR: 0.005687
Training Epoch: 1 [3584/54000]	Loss: 2.1773	LR: 0.006161
Training Epoch: 1 [3840/54000]	Loss: 2.1590	LR: 0.006635
Training Epoch: 1 [4096/54000]	Loss: 2.1471	LR: 0.007109
Training Epoch: 1 [4352/54000]	Loss: 2.1381	LR: 0.007583
Training Epoch: 1 [4608/54000]	Loss: 2.1201	LR: 0.008057
Training Epoch: 1 [4864/54000]	Loss: 2.0751	LR: 0.008531
Training Epoch: 1 [5120/54000]	Loss: 2.0283	LR: 0.009005
Training Epoch: 1 [5376/54000]	Loss: 2.0222	LR: 0.009479
Training Epoch: 1 [5632/54000]	Loss: 1.9703	LR: 0.009953
Training Epoch: 1 [5888/54000]	Loss: 1.9859	LR: 0.010427
Training Epoch: 1 [6144/54000]	Loss: 1.9487	LR: 0.010900
Training Epoch: 1 [6400/54000]	Loss: 1.9191	LR: 0.011374
Training Epoch: 1 [6656/54000]	Loss: 1.8443	LR: 0.011848
Training Epoch: 1 [6912/54000]	Loss: 1.8341	LR: 0.012322
Training Epoch: 1 [7168/54000]	Loss: 1.7876	LR: 0.012796
Training Epoch: 1 [7424/54000]	Loss: 1.7646	LR: 0.013270
Training Epoch: 1 [7680/54000]	Loss: 1.7589	LR: 0.013744
Training Epoch: 1 [7936/54000]	Loss: 1.6480	LR: 0.014218
Training Epoch: 1 [8192/54000]	Loss: 1.6429	LR: 0.014692
Training Epoch: 1 [8448/54000]	Loss: 1.5812	LR: 0.015166
Training Epoch: 1 [8704/54000]	Loss: 1.5373	LR: 0.015640
Training Epoch: 1 [8960/54000]	Loss: 1.4262	LR: 0.016114
Training Epoch: 1 [9216/54000]	Loss: 1.4637	LR: 0.016588
Training Epoch: 1 [9472/54000]	Loss: 1.3696	LR: 0.017062
Training Epoch: 1 [9728/54000]	Loss: 1.3279	LR: 0.017536
Training Epoch: 1 [9984/54000]	Loss: 1.2379	LR: 0.018009
Training Epoch: 1 [10240/54000]	Loss: 1.1742	LR: 0.018483
Training Epoch: 1 [10496/54000]	Loss: 1.1332	LR: 0.018957
Training Epoch: 1 [10752/54000]	Loss: 1.1244	LR: 0.019431
Training Epoch: 1 [11008/54000]	Loss: 1.0251	LR: 0.019905
Training Epoch: 1 [11264/54000]	Loss: 0.9648	LR: 0.020379
Training Epoch: 1 [11520/54000]	Loss: 0.9121	LR: 0.020853
Training Epoch: 1 [11776/54000]	Loss: 0.8625	LR: 0.021327
Training Epoch: 1 [12032/54000]	Loss: 0.8315	LR: 0.021801
Training Epoch: 1 [12288/54000]	Loss: 0.7361	LR: 0.022275
Training Epoch: 1 [12544/54000]	Loss: 0.7480	LR: 0.022749
Training Epoch: 1 [12800/54000]	Loss: 0.7441	LR: 0.023223
Training Epoch: 1 [13056/54000]	Loss: 0.6212	LR: 0.023697
Training Epoch: 1 [13312/54000]	Loss: 0.5509	LR: 0.024171
Training Epoch: 1 [13568/54000]	Loss: 0.5320	LR: 0.024645
Training Epoch: 1 [13824/54000]	Loss: 0.5608	LR: 0.025118
Training Epoch: 1 [14080/54000]	Loss: 0.5290	LR: 0.025592
Training Epoch: 1 [14336/54000]	Loss: 0.4849	LR: 0.026066
Training Epoch: 1 [14592/54000]	Loss: 0.4543	LR: 0.026540
Training Epoch: 1 [14848/54000]	Loss: 0.4027	LR: 0.027014
Training Epoch: 1 [15104/54000]	Loss: 0.3632	LR: 0.027488
Training Epoch: 1 [15360/54000]	Loss: 0.3593	LR: 0.027962
Training Epoch: 1 [15616/54000]	Loss: 0.4282	LR: 0.028436
Training Epoch: 1 [15872/54000]	Loss: 0.3760	LR: 0.028910
Training Epoch: 1 [16128/54000]	Loss: 0.3395	LR: 0.029384
Training Epoch: 1 [16384/54000]	Loss: 0.3200	LR: 0.029858
Training Epoch: 1 [16640/54000]	Loss: 0.2715	LR: 0.030332
Training Epoch: 1 [16896/54000]	Loss: 0.3369	LR: 0.030806
Training Epoch: 1 [17152/54000]	Loss: 0.2227	LR: 0.031280
Training Epoch: 1 [17408/54000]	Loss: 0.3111	LR: 0.031754
Training Epoch: 1 [17664/54000]	Loss: 0.2326	LR: 0.032227
Training Epoch: 1 [17920/54000]	Loss: 0.2720	LR: 0.032701
Training Epoch: 1 [18176/54000]	Loss: 0.2268	LR: 0.033175
Training Epoch: 1 [18432/54000]	Loss: 0.2354	LR: 0.033649
Training Epoch: 1 [18688/54000]	Loss: 0.2987	LR: 0.034123
Training Epoch: 1 [18944/54000]	Loss: 0.2198	LR: 0.034597
Training Epoch: 1 [19200/54000]	Loss: 0.2084	LR: 0.035071
Training Epoch: 1 [19456/54000]	Loss: 0.2357	LR: 0.035545
Training Epoch: 1 [19712/54000]	Loss: 0.2612	LR: 0.036019
Training Epoch: 1 [19968/54000]	Loss: 0.2327	LR: 0.036493
Training Epoch: 1 [20224/54000]	Loss: 0.3380	LR: 0.036967
Training Epoch: 1 [20480/54000]	Loss: 0.2563	LR: 0.037441
Training Epoch: 1 [20736/54000]	Loss: 0.3137	LR: 0.037915
Training Epoch: 1 [20992/54000]	Loss: 0.2030	LR: 0.038389
Training Epoch: 1 [21248/54000]	Loss: 0.1982	LR: 0.038863
Training Epoch: 1 [21504/54000]	Loss: 0.2494	LR: 0.039336
Training Epoch: 1 [21760/54000]	Loss: 0.1880	LR: 0.039810
Training Epoch: 1 [22016/54000]	Loss: 0.1371	LR: 0.040284
Training Epoch: 1 [22272/54000]	Loss: 0.2262	LR: 0.040758
Training Epoch: 1 [22528/54000]	Loss: 0.1892	LR: 0.041232
Training Epoch: 1 [22784/54000]	Loss: 0.1801	LR: 0.041706
Training Epoch: 1 [23040/54000]	Loss: 0.1811	LR: 0.042180
Training Epoch: 1 [23296/54000]	Loss: 0.2038	LR: 0.042654
Training Epoch: 1 [23552/54000]	Loss: 0.1658	LR: 0.043128
Training Epoch: 1 [23808/54000]	Loss: 0.1770	LR: 0.043602
Training Epoch: 1 [24064/54000]	Loss: 0.1469	LR: 0.044076
Training Epoch: 1 [24320/54000]	Loss: 0.2073	LR: 0.044550
Training Epoch: 1 [24576/54000]	Loss: 0.1468	LR: 0.045024
Training Epoch: 1 [24832/54000]	Loss: 0.1455	LR: 0.045498
Training Epoch: 1 [25088/54000]	Loss: 0.1242	LR: 0.045972
Training Epoch: 1 [25344/54000]	Loss: 0.1815	LR: 0.046445
Training Epoch: 1 [25600/54000]	Loss: 0.1093	LR: 0.046919
Training Epoch: 1 [25856/54000]	Loss: 0.1467	LR: 0.047393
Training Epoch: 1 [26112/54000]	Loss: 0.1043	LR: 0.047867
Training Epoch: 1 [26368/54000]	Loss: 0.1526	LR: 0.048341
Training Epoch: 1 [26624/54000]	Loss: 0.1687	LR: 0.048815
Training Epoch: 1 [26880/54000]	Loss: 0.1580	LR: 0.049289
Training Epoch: 1 [27136/54000]	Loss: 0.1044	LR: 0.049763
Training Epoch: 1 [27392/54000]	Loss: 0.1205	LR: 0.050237
Training Epoch: 1 [27648/54000]	Loss: 0.1512	LR: 0.050711
Training Epoch: 1 [27904/54000]	Loss: 0.1269	LR: 0.051185
Training Epoch: 1 [28160/54000]	Loss: 0.1466	LR: 0.051659
Training Epoch: 1 [28416/54000]	Loss: 0.1311	LR: 0.052133
Training Epoch: 1 [28672/54000]	Loss: 0.1487	LR: 0.052607
Training Epoch: 1 [28928/54000]	Loss: 0.1765	LR: 0.053081
Training Epoch: 1 [29184/54000]	Loss: 0.1385	LR: 0.053555
Training Epoch: 1 [29440/54000]	Loss: 0.0944	LR: 0.054028
Training Epoch: 1 [29696/54000]	Loss: 0.0939	LR: 0.054502
Training Epoch: 1 [29952/54000]	Loss: 0.1216	LR: 0.054976
Training Epoch: 1 [30208/54000]	Loss: 0.1176	LR: 0.055450
Training Epoch: 1 [30464/54000]	Loss: 0.1224	LR: 0.055924
Training Epoch: 1 [30720/54000]	Loss: 0.1092	LR: 0.056398
Training Epoch: 1 [30976/54000]	Loss: 0.0896	LR: 0.056872
Training Epoch: 1 [31232/54000]	Loss: 0.0994	LR: 0.057346
Training Epoch: 1 [31488/54000]	Loss: 0.1736	LR: 0.057820
Training Epoch: 1 [31744/54000]	Loss: 0.1001	LR: 0.058294
Training Epoch: 1 [32000/54000]	Loss: 0.1460	LR: 0.058768
Training Epoch: 1 [32256/54000]	Loss: 0.0993	LR: 0.059242
Training Epoch: 1 [32512/54000]	Loss: 0.1157	LR: 0.059716
Training Epoch: 1 [32768/54000]	Loss: 0.0978	LR: 0.060190
Training Epoch: 1 [33024/54000]	Loss: 0.1091	LR: 0.060664
Training Epoch: 1 [33280/54000]	Loss: 0.1302	LR: 0.061137
Training Epoch: 1 [33536/54000]	Loss: 0.0678	LR: 0.061611
Training Epoch: 1 [33792/54000]	Loss: 0.1181	LR: 0.062085
Training Epoch: 1 [34048/54000]	Loss: 0.1120	LR: 0.062559
Training Epoch: 1 [34304/54000]	Loss: 0.1111	LR: 0.063033
Training Epoch: 1 [34560/54000]	Loss: 0.1343	LR: 0.063507
Training Epoch: 1 [34816/54000]	Loss: 0.0915	LR: 0.063981
Training Epoch: 1 [35072/54000]	Loss: 0.0755	LR: 0.064455
Training Epoch: 1 [35328/54000]	Loss: 0.0827	LR: 0.064929
Training Epoch: 1 [35584/54000]	Loss: 0.0577	LR: 0.065403
Training Epoch: 1 [35840/54000]	Loss: 0.1330	LR: 0.065877
Training Epoch: 1 [36096/54000]	Loss: 0.1085	LR: 0.066351
Training Epoch: 1 [36352/54000]	Loss: 0.0792	LR: 0.066825
Training Epoch: 1 [36608/54000]	Loss: 0.1178	LR: 0.067299
Training Epoch: 1 [36864/54000]	Loss: 0.1236	LR: 0.067773
Training Epoch: 1 [37120/54000]	Loss: 0.0624	LR: 0.068246
Training Epoch: 1 [37376/54000]	Loss: 0.0735	LR: 0.068720
Training Epoch: 1 [37632/54000]	Loss: 0.0621	LR: 0.069194
Training Epoch: 1 [37888/54000]	Loss: 0.0699	LR: 0.069668
Training Epoch: 1 [38144/54000]	Loss: 0.1194	LR: 0.070142
Training Epoch: 1 [38400/54000]	Loss: 0.1009	LR: 0.070616
Training Epoch: 1 [38656/54000]	Loss: 0.1028	LR: 0.071090
Training Epoch: 1 [38912/54000]	Loss: 0.0415	LR: 0.071564
Training Epoch: 1 [39168/54000]	Loss: 0.0815	LR: 0.072038
Training Epoch: 1 [39424/54000]	Loss: 0.0875	LR: 0.072512
Training Epoch: 1 [39680/54000]	Loss: 0.1371	LR: 0.072986
Training Epoch: 1 [39936/54000]	Loss: 0.0984	LR: 0.073460
Training Epoch: 1 [40192/54000]	Loss: 0.1285	LR: 0.073934
Training Epoch: 1 [40448/54000]	Loss: 0.0611	LR: 0.074408
Training Epoch: 1 [40704/54000]	Loss: 0.0922	LR: 0.074882
Training Epoch: 1 [40960/54000]	Loss: 0.1165	LR: 0.075355
Training Epoch: 1 [41216/54000]	Loss: 0.0749	LR: 0.075829
Training Epoch: 1 [41472/54000]	Loss: 0.0952	LR: 0.076303
Training Epoch: 1 [41728/54000]	Loss: 0.0598	LR: 0.076777
Training Epoch: 1 [41984/54000]	Loss: 0.0830	LR: 0.077251
Training Epoch: 1 [42240/54000]	Loss: 0.0718	LR: 0.077725
Training Epoch: 1 [42496/54000]	Loss: 0.0984	LR: 0.078199
Training Epoch: 1 [42752/54000]	Loss: 0.0725	LR: 0.078673
Training Epoch: 1 [43008/54000]	Loss: 0.0600	LR: 0.079147
Training Epoch: 1 [43264/54000]	Loss: 0.0487	LR: 0.079621
Training Epoch: 1 [43520/54000]	Loss: 0.1685	LR: 0.080095
Training Epoch: 1 [43776/54000]	Loss: 0.0841	LR: 0.080569
Training Epoch: 1 [44032/54000]	Loss: 0.0638	LR: 0.081043
Training Epoch: 1 [44288/54000]	Loss: 0.1444	LR: 0.081517
Training Epoch: 1 [44544/54000]	Loss: 0.0759	LR: 0.081991
Training Epoch: 1 [44800/54000]	Loss: 0.0745	LR: 0.082464
Training Epoch: 1 [45056/54000]	Loss: 0.0993	LR: 0.082938
Training Epoch: 1 [45312/54000]	Loss: 0.1123	LR: 0.083412
Training Epoch: 1 [45568/54000]	Loss: 0.0481	LR: 0.083886
Training Epoch: 1 [45824/54000]	Loss: 0.1001	LR: 0.084360
Training Epoch: 1 [46080/54000]	Loss: 0.0490	LR: 0.084834
Training Epoch: 1 [46336/54000]	Loss: 0.0847	LR: 0.085308
Training Epoch: 1 [46592/54000]	Loss: 0.0574	LR: 0.085782
Training Epoch: 1 [46848/54000]	Loss: 0.1319	LR: 0.086256
Training Epoch: 1 [47104/54000]	Loss: 0.0728	LR: 0.086730
Training Epoch: 1 [47360/54000]	Loss: 0.1052	LR: 0.087204
Training Epoch: 1 [47616/54000]	Loss: 0.0966	LR: 0.087678
Training Epoch: 1 [47872/54000]	Loss: 0.1011	LR: 0.088152
Training Epoch: 1 [48128/54000]	Loss: 0.0790	LR: 0.088626
Training Epoch: 1 [48384/54000]	Loss: 0.0540	LR: 0.089100
Training Epoch: 1 [48640/54000]	Loss: 0.0572	LR: 0.089573
Training Epoch: 1 [48896/54000]	Loss: 0.0919	LR: 0.090047
Training Epoch: 1 [49152/54000]	Loss: 0.0640	LR: 0.090521
Training Epoch: 1 [49408/54000]	Loss: 0.1129	LR: 0.090995
Training Epoch: 1 [49664/54000]	Loss: 0.1475	LR: 0.091469
Training Epoch: 1 [49920/54000]	Loss: 0.0601	LR: 0.091943
Training Epoch: 1 [50176/54000]	Loss: 0.0661	LR: 0.092417
Training Epoch: 1 [50432/54000]	Loss: 0.0594	LR: 0.092891
Training Epoch: 1 [50688/54000]	Loss: 0.0524	LR: 0.093365
Training Epoch: 1 [50944/54000]	Loss: 0.0481	LR: 0.093839
Training Epoch: 1 [51200/54000]	Loss: 0.1072	LR: 0.094313
Training Epoch: 1 [51456/54000]	Loss: 0.1200	LR: 0.094787
Training Epoch: 1 [51712/54000]	Loss: 0.1136	LR: 0.095261
Training Epoch: 1 [51968/54000]	Loss: 0.0613	LR: 0.095735
Training Epoch: 1 [52224/54000]	Loss: 0.1068	LR: 0.096209
Training Epoch: 1 [52480/54000]	Loss: 0.0602	LR: 0.096682
Training Epoch: 1 [52736/54000]	Loss: 0.0726	LR: 0.097156
Training Epoch: 1 [52992/54000]	Loss: 0.1110	LR: 0.097630
Training Epoch: 1 [53248/54000]	Loss: 0.0986	LR: 0.098104
Training Epoch: 1 [53504/54000]	Loss: 0.0759	LR: 0.098578
Training Epoch: 1 [53760/54000]	Loss: 0.0994	LR: 0.099052
Training Epoch: 1 [54000/54000]	Loss: 0.1085	LR: 0.099526
Epoch 1 - Average Train Loss: 0.5317, Train Accuracy: 0.8481
Epoch 1 training time consumed: 39.38s
Evaluating Network.....
Test set: Epoch: 1, Average loss: 0.0006, Accuracy: 0.9529, Time consumed:2.82s
Saving weights file to checkpoint/retrain/AllCNN/Wednesday_23_July_2025_06h_24m_42s/AllCNN-Mnist-seed1-ret100-1-best.pth
Training Epoch: 2 [256/54000]	Loss: 0.0405	LR: 0.020000
Training Epoch: 2 [512/54000]	Loss: 0.0282	LR: 0.020000
Training Epoch: 2 [768/54000]	Loss: 0.0855	LR: 0.020000
Training Epoch: 2 [1024/54000]	Loss: 0.0607	LR: 0.020000
Training Epoch: 2 [1280/54000]	Loss: 0.0403	LR: 0.020000
Training Epoch: 2 [1536/54000]	Loss: 0.0604	LR: 0.020000
Training Epoch: 2 [1792/54000]	Loss: 0.0496	LR: 0.020000
Training Epoch: 2 [2048/54000]	Loss: 0.0628	LR: 0.020000
Training Epoch: 2 [2304/54000]	Loss: 0.0512	LR: 0.020000
Training Epoch: 2 [2560/54000]	Loss: 0.0384	LR: 0.020000
Training Epoch: 2 [2816/54000]	Loss: 0.0588	LR: 0.020000
Training Epoch: 2 [3072/54000]	Loss: 0.0213	LR: 0.020000
Training Epoch: 2 [3328/54000]	Loss: 0.0346	LR: 0.020000
Training Epoch: 2 [3584/54000]	Loss: 0.0230	LR: 0.020000
Training Epoch: 2 [3840/54000]	Loss: 0.1012	LR: 0.020000
Training Epoch: 2 [4096/54000]	Loss: 0.0500	LR: 0.020000
Training Epoch: 2 [4352/54000]	Loss: 0.1057	LR: 0.020000
Training Epoch: 2 [4608/54000]	Loss: 0.0372	LR: 0.020000
Training Epoch: 2 [4864/54000]	Loss: 0.0291	LR: 0.020000
Training Epoch: 2 [5120/54000]	Loss: 0.0609	LR: 0.020000
Training Epoch: 2 [5376/54000]	Loss: 0.0628	LR: 0.020000
Training Epoch: 2 [5632/54000]	Loss: 0.0796	LR: 0.020000
Training Epoch: 2 [5888/54000]	Loss: 0.0588	LR: 0.020000
Training Epoch: 2 [6144/54000]	Loss: 0.0491	LR: 0.020000
Training Epoch: 2 [6400/54000]	Loss: 0.0258	LR: 0.020000
Training Epoch: 2 [6656/54000]	Loss: 0.0372	LR: 0.020000
Training Epoch: 2 [6912/54000]	Loss: 0.0515	LR: 0.020000
Training Epoch: 2 [7168/54000]	Loss: 0.0373	LR: 0.020000
Training Epoch: 2 [7424/54000]	Loss: 0.0533	LR: 0.020000
Training Epoch: 2 [7680/54000]	Loss: 0.0836	LR: 0.020000
Training Epoch: 2 [7936/54000]	Loss: 0.0428	LR: 0.020000
Training Epoch: 2 [8192/54000]	Loss: 0.0462	LR: 0.020000
Training Epoch: 2 [8448/54000]	Loss: 0.0481	LR: 0.020000
Training Epoch: 2 [8704/54000]	Loss: 0.0748	LR: 0.020000
Training Epoch: 2 [8960/54000]	Loss: 0.0287	LR: 0.020000
Training Epoch: 2 [9216/54000]	Loss: 0.1047	LR: 0.020000
Training Epoch: 2 [9472/54000]	Loss: 0.0441	LR: 0.020000
Training Epoch: 2 [9728/54000]	Loss: 0.0425	LR: 0.020000
Training Epoch: 2 [9984/54000]	Loss: 0.0528	LR: 0.020000
Training Epoch: 2 [10240/54000]	Loss: 0.0327	LR: 0.020000
Training Epoch: 2 [10496/54000]	Loss: 0.0306	LR: 0.020000
Training Epoch: 2 [10752/54000]	Loss: 0.0611	LR: 0.020000
Training Epoch: 2 [11008/54000]	Loss: 0.0340	LR: 0.020000
Training Epoch: 2 [11264/54000]	Loss: 0.0370	LR: 0.020000
Training Epoch: 2 [11520/54000]	Loss: 0.0153	LR: 0.020000
Training Epoch: 2 [11776/54000]	Loss: 0.0414	LR: 0.020000
Training Epoch: 2 [12032/54000]	Loss: 0.0486	LR: 0.020000
Training Epoch: 2 [12288/54000]	Loss: 0.0319	LR: 0.020000
Training Epoch: 2 [12544/54000]	Loss: 0.0514	LR: 0.020000
Training Epoch: 2 [12800/54000]	Loss: 0.0305	LR: 0.020000
Training Epoch: 2 [13056/54000]	Loss: 0.0737	LR: 0.020000
Training Epoch: 2 [13312/54000]	Loss: 0.0286	LR: 0.020000
Training Epoch: 2 [13568/54000]	Loss: 0.0414	LR: 0.020000
Training Epoch: 2 [13824/54000]	Loss: 0.0267	LR: 0.020000
Training Epoch: 2 [14080/54000]	Loss: 0.0542	LR: 0.020000
Training Epoch: 2 [14336/54000]	Loss: 0.0440	LR: 0.020000
Training Epoch: 2 [14592/54000]	Loss: 0.0292	LR: 0.020000
Training Epoch: 2 [14848/54000]	Loss: 0.0425	LR: 0.020000
Training Epoch: 2 [15104/54000]	Loss: 0.0705	LR: 0.020000
Training Epoch: 2 [15360/54000]	Loss: 0.0532	LR: 0.020000
Training Epoch: 2 [15616/54000]	Loss: 0.0404	LR: 0.020000
Training Epoch: 2 [15872/54000]	Loss: 0.0820	LR: 0.020000
Training Epoch: 2 [16128/54000]	Loss: 0.0285	LR: 0.020000
Training Epoch: 2 [16384/54000]	Loss: 0.0310	LR: 0.020000
Training Epoch: 2 [16640/54000]	Loss: 0.0372	LR: 0.020000
Training Epoch: 2 [16896/54000]	Loss: 0.0496	LR: 0.020000
Training Epoch: 2 [17152/54000]	Loss: 0.0492	LR: 0.020000
Training Epoch: 2 [17408/54000]	Loss: 0.0469	LR: 0.020000
Training Epoch: 2 [17664/54000]	Loss: 0.0450	LR: 0.020000
Training Epoch: 2 [17920/54000]	Loss: 0.0247	LR: 0.020000
Training Epoch: 2 [18176/54000]	Loss: 0.0336	LR: 0.020000
Training Epoch: 2 [18432/54000]	Loss: 0.0654	LR: 0.020000
Training Epoch: 2 [18688/54000]	Loss: 0.0758	LR: 0.020000
Training Epoch: 2 [18944/54000]	Loss: 0.0557	LR: 0.020000
Training Epoch: 2 [19200/54000]	Loss: 0.0487	LR: 0.020000
Training Epoch: 2 [19456/54000]	Loss: 0.0294	LR: 0.020000
Training Epoch: 2 [19712/54000]	Loss: 0.0272	LR: 0.020000
Training Epoch: 2 [19968/54000]	Loss: 0.0608	LR: 0.020000
Training Epoch: 2 [20224/54000]	Loss: 0.0270	LR: 0.020000
Training Epoch: 2 [20480/54000]	Loss: 0.0409	LR: 0.020000
Training Epoch: 2 [20736/54000]	Loss: 0.0347	LR: 0.020000
Training Epoch: 2 [20992/54000]	Loss: 0.0316	LR: 0.020000
Training Epoch: 2 [21248/54000]	Loss: 0.0474	LR: 0.020000
Training Epoch: 2 [21504/54000]	Loss: 0.0599	LR: 0.020000
Training Epoch: 2 [21760/54000]	Loss: 0.0476	LR: 0.020000
Training Epoch: 2 [22016/54000]	Loss: 0.0196	LR: 0.020000
Training Epoch: 2 [22272/54000]	Loss: 0.0415	LR: 0.020000
Training Epoch: 2 [22528/54000]	Loss: 0.0366	LR: 0.020000
Training Epoch: 2 [22784/54000]	Loss: 0.0805	LR: 0.020000
Training Epoch: 2 [23040/54000]	Loss: 0.0421	LR: 0.020000
Training Epoch: 2 [23296/54000]	Loss: 0.0324	LR: 0.020000
Training Epoch: 2 [23552/54000]	Loss: 0.0295	LR: 0.020000
Training Epoch: 2 [23808/54000]	Loss: 0.0574	LR: 0.020000
Training Epoch: 2 [24064/54000]	Loss: 0.0434	LR: 0.020000
Training Epoch: 2 [24320/54000]	Loss: 0.0334	LR: 0.020000
Training Epoch: 2 [24576/54000]	Loss: 0.0225	LR: 0.020000
Training Epoch: 2 [24832/54000]	Loss: 0.0402	LR: 0.020000
Training Epoch: 2 [25088/54000]	Loss: 0.0638	LR: 0.020000
Training Epoch: 2 [25344/54000]	Loss: 0.0475	LR: 0.020000
Training Epoch: 2 [25600/54000]	Loss: 0.0306	LR: 0.020000
Training Epoch: 2 [25856/54000]	Loss: 0.0415	LR: 0.020000
Training Epoch: 2 [26112/54000]	Loss: 0.0567	LR: 0.020000
Training Epoch: 2 [26368/54000]	Loss: 0.0500	LR: 0.020000
Training Epoch: 2 [26624/54000]	Loss: 0.0244	LR: 0.020000
Training Epoch: 2 [26880/54000]	Loss: 0.0287	LR: 0.020000
Training Epoch: 2 [27136/54000]	Loss: 0.0482	LR: 0.020000
Training Epoch: 2 [27392/54000]	Loss: 0.0263	LR: 0.020000
Training Epoch: 2 [27648/54000]	Loss: 0.0495	LR: 0.020000
Training Epoch: 2 [27904/54000]	Loss: 0.0266	LR: 0.020000
Training Epoch: 2 [28160/54000]	Loss: 0.0375	LR: 0.020000
Training Epoch: 2 [28416/54000]	Loss: 0.0655	LR: 0.020000
Training Epoch: 2 [28672/54000]	Loss: 0.0268	LR: 0.020000
Training Epoch: 2 [28928/54000]	Loss: 0.0453	LR: 0.020000
Training Epoch: 2 [29184/54000]	Loss: 0.0555	LR: 0.020000
Training Epoch: 2 [29440/54000]	Loss: 0.0376	LR: 0.020000
Training Epoch: 2 [29696/54000]	Loss: 0.0488	LR: 0.020000
Training Epoch: 2 [29952/54000]	Loss: 0.0631	LR: 0.020000
Training Epoch: 2 [30208/54000]	Loss: 0.0362	LR: 0.020000
Training Epoch: 2 [30464/54000]	Loss: 0.0318	LR: 0.020000
Training Epoch: 2 [30720/54000]	Loss: 0.0110	LR: 0.020000
Training Epoch: 2 [30976/54000]	Loss: 0.0465	LR: 0.020000
Training Epoch: 2 [31232/54000]	Loss: 0.0518	LR: 0.020000
Training Epoch: 2 [31488/54000]	Loss: 0.0251	LR: 0.020000
Training Epoch: 2 [31744/54000]	Loss: 0.0672	LR: 0.020000
Training Epoch: 2 [32000/54000]	Loss: 0.0395	LR: 0.020000
Training Epoch: 2 [32256/54000]	Loss: 0.0162	LR: 0.020000
Training Epoch: 2 [32512/54000]	Loss: 0.0314	LR: 0.020000
Training Epoch: 2 [32768/54000]	Loss: 0.0163	LR: 0.020000
Training Epoch: 2 [33024/54000]	Loss: 0.0316	LR: 0.020000
Training Epoch: 2 [33280/54000]	Loss: 0.0348	LR: 0.020000
Training Epoch: 2 [33536/54000]	Loss: 0.0278	LR: 0.020000
Training Epoch: 2 [33792/54000]	Loss: 0.0523	LR: 0.020000
Training Epoch: 2 [34048/54000]	Loss: 0.0142	LR: 0.020000
Training Epoch: 2 [34304/54000]	Loss: 0.0245	LR: 0.020000
Training Epoch: 2 [34560/54000]	Loss: 0.0501	LR: 0.020000
Training Epoch: 2 [34816/54000]	Loss: 0.0155	LR: 0.020000
Training Epoch: 2 [35072/54000]	Loss: 0.0554	LR: 0.020000
Training Epoch: 2 [35328/54000]	Loss: 0.0263	LR: 0.020000
Training Epoch: 2 [35584/54000]	Loss: 0.0171	LR: 0.020000
Training Epoch: 2 [35840/54000]	Loss: 0.0246	LR: 0.020000
Training Epoch: 2 [36096/54000]	Loss: 0.0171	LR: 0.020000
Training Epoch: 2 [36352/54000]	Loss: 0.0243	LR: 0.020000
Training Epoch: 2 [36608/54000]	Loss: 0.0408	LR: 0.020000
Training Epoch: 2 [36864/54000]	Loss: 0.0580	LR: 0.020000
Training Epoch: 2 [37120/54000]	Loss: 0.0206	LR: 0.020000
Training Epoch: 2 [37376/54000]	Loss: 0.0173	LR: 0.020000
Training Epoch: 2 [37632/54000]	Loss: 0.0122	LR: 0.020000
Training Epoch: 2 [37888/54000]	Loss: 0.0444	LR: 0.020000
Training Epoch: 2 [38144/54000]	Loss: 0.0202	LR: 0.020000
Training Epoch: 2 [38400/54000]	Loss: 0.0368	LR: 0.020000
Training Epoch: 2 [38656/54000]	Loss: 0.0471	LR: 0.020000
Training Epoch: 2 [38912/54000]	Loss: 0.0391	LR: 0.020000
Training Epoch: 2 [39168/54000]	Loss: 0.0249	LR: 0.020000
Training Epoch: 2 [39424/54000]	Loss: 0.0536	LR: 0.020000
Training Epoch: 2 [39680/54000]	Loss: 0.0210	LR: 0.020000
Training Epoch: 2 [39936/54000]	Loss: 0.0200	LR: 0.020000
Training Epoch: 2 [40192/54000]	Loss: 0.0330	LR: 0.020000
Training Epoch: 2 [40448/54000]	Loss: 0.0231	LR: 0.020000
Training Epoch: 2 [40704/54000]	Loss: 0.0379	LR: 0.020000
Training Epoch: 2 [40960/54000]	Loss: 0.0192	LR: 0.020000
Training Epoch: 2 [41216/54000]	Loss: 0.0281	LR: 0.020000
Training Epoch: 2 [41472/54000]	Loss: 0.0320	LR: 0.020000
Training Epoch: 2 [41728/54000]	Loss: 0.0617	LR: 0.020000
Training Epoch: 2 [41984/54000]	Loss: 0.0191	LR: 0.020000
Training Epoch: 2 [42240/54000]	Loss: 0.0428	LR: 0.020000
Training Epoch: 2 [42496/54000]	Loss: 0.0247	LR: 0.020000
Training Epoch: 2 [42752/54000]	Loss: 0.0296	LR: 0.020000
Training Epoch: 2 [43008/54000]	Loss: 0.0241	LR: 0.020000
Training Epoch: 2 [43264/54000]	Loss: 0.0577	LR: 0.020000
Training Epoch: 2 [43520/54000]	Loss: 0.0233	LR: 0.020000
Training Epoch: 2 [43776/54000]	Loss: 0.0888	LR: 0.020000
Training Epoch: 2 [44032/54000]	Loss: 0.0122	LR: 0.020000
Training Epoch: 2 [44288/54000]	Loss: 0.0258	LR: 0.020000
Training Epoch: 2 [44544/54000]	Loss: 0.0434	LR: 0.020000
Training Epoch: 2 [44800/54000]	Loss: 0.0558	LR: 0.020000
Training Epoch: 2 [45056/54000]	Loss: 0.0931	LR: 0.020000
Training Epoch: 2 [45312/54000]	Loss: 0.0383	LR: 0.020000
Training Epoch: 2 [45568/54000]	Loss: 0.0258	LR: 0.020000
Training Epoch: 2 [45824/54000]	Loss: 0.0263	LR: 0.020000
Training Epoch: 2 [46080/54000]	Loss: 0.0416	LR: 0.020000
Training Epoch: 2 [46336/54000]	Loss: 0.0393	LR: 0.020000
Training Epoch: 2 [46592/54000]	Loss: 0.0295	LR: 0.020000
Training Epoch: 2 [46848/54000]	Loss: 0.0303	LR: 0.020000
Training Epoch: 2 [47104/54000]	Loss: 0.0217	LR: 0.020000
Training Epoch: 2 [47360/54000]	Loss: 0.0278	LR: 0.020000
Training Epoch: 2 [47616/54000]	Loss: 0.0333	LR: 0.020000
Training Epoch: 2 [47872/54000]	Loss: 0.0294	LR: 0.020000
Training Epoch: 2 [48128/54000]	Loss: 0.0341	LR: 0.020000
Training Epoch: 2 [48384/54000]	Loss: 0.0371	LR: 0.020000
Training Epoch: 2 [48640/54000]	Loss: 0.0205	LR: 0.020000
Training Epoch: 2 [48896/54000]	Loss: 0.0317	LR: 0.020000
Training Epoch: 2 [49152/54000]	Loss: 0.0596	LR: 0.020000
Training Epoch: 2 [49408/54000]	Loss: 0.0526	LR: 0.020000
Training Epoch: 2 [49664/54000]	Loss: 0.0371	LR: 0.020000
Training Epoch: 2 [49920/54000]	Loss: 0.0310	LR: 0.020000
Training Epoch: 2 [50176/54000]	Loss: 0.0553	LR: 0.020000
Training Epoch: 2 [50432/54000]	Loss: 0.0251	LR: 0.020000
Training Epoch: 2 [50688/54000]	Loss: 0.0213	LR: 0.020000
Training Epoch: 2 [50944/54000]	Loss: 0.0308	LR: 0.020000
Training Epoch: 2 [51200/54000]	Loss: 0.0346	LR: 0.020000
Training Epoch: 2 [51456/54000]	Loss: 0.0241	LR: 0.020000
Training Epoch: 2 [51712/54000]	Loss: 0.0352	LR: 0.020000
Training Epoch: 2 [51968/54000]	Loss: 0.0245	LR: 0.020000
Training Epoch: 2 [52224/54000]	Loss: 0.0302	LR: 0.020000
Training Epoch: 2 [52480/54000]	Loss: 0.0310	LR: 0.020000
Training Epoch: 2 [52736/54000]	Loss: 0.0380	LR: 0.020000
Training Epoch: 2 [52992/54000]	Loss: 0.0107	LR: 0.020000
Training Epoch: 2 [53248/54000]	Loss: 0.0287	LR: 0.020000
Training Epoch: 2 [53504/54000]	Loss: 0.0203	LR: 0.020000
Training Epoch: 2 [53760/54000]	Loss: 0.0220	LR: 0.020000
Training Epoch: 2 [54000/54000]	Loss: 0.0107	LR: 0.020000
Epoch 2 - Average Train Loss: 0.0404, Train Accuracy: 0.9887
Epoch 2 training time consumed: 38.12s
Evaluating Network.....
Test set: Epoch: 2, Average loss: 0.0001, Accuracy: 0.9937, Time consumed:1.59s
Saving weights file to checkpoint/retrain/AllCNN/Wednesday_23_July_2025_06h_24m_42s/AllCNN-Mnist-seed1-ret100-2-best.pth
Training Epoch: 3 [256/54000]	Loss: 0.0169	LR: 0.004000
Training Epoch: 3 [512/54000]	Loss: 0.0232	LR: 0.004000
Training Epoch: 3 [768/54000]	Loss: 0.0527	LR: 0.004000
Training Epoch: 3 [1024/54000]	Loss: 0.0436	LR: 0.004000
Training Epoch: 3 [1280/54000]	Loss: 0.0514	LR: 0.004000
Training Epoch: 3 [1536/54000]	Loss: 0.0441	LR: 0.004000
Training Epoch: 3 [1792/54000]	Loss: 0.0176	LR: 0.004000
Training Epoch: 3 [2048/54000]	Loss: 0.0422	LR: 0.004000
Training Epoch: 3 [2304/54000]	Loss: 0.0172	LR: 0.004000
Training Epoch: 3 [2560/54000]	Loss: 0.0189	LR: 0.004000
Training Epoch: 3 [2816/54000]	Loss: 0.0225	LR: 0.004000
Training Epoch: 3 [3072/54000]	Loss: 0.0382	LR: 0.004000
Training Epoch: 3 [3328/54000]	Loss: 0.0163	LR: 0.004000
Training Epoch: 3 [3584/54000]	Loss: 0.0358	LR: 0.004000
Training Epoch: 3 [3840/54000]	Loss: 0.0518	LR: 0.004000
Training Epoch: 3 [4096/54000]	Loss: 0.0564	LR: 0.004000
Training Epoch: 3 [4352/54000]	Loss: 0.0285	LR: 0.004000
Training Epoch: 3 [4608/54000]	Loss: 0.0198	LR: 0.004000
Training Epoch: 3 [4864/54000]	Loss: 0.0284	LR: 0.004000
Training Epoch: 3 [5120/54000]	Loss: 0.0123	LR: 0.004000
Training Epoch: 3 [5376/54000]	Loss: 0.0311	LR: 0.004000
Training Epoch: 3 [5632/54000]	Loss: 0.0443	LR: 0.004000
Training Epoch: 3 [5888/54000]	Loss: 0.0151	LR: 0.004000
Training Epoch: 3 [6144/54000]	Loss: 0.0218	LR: 0.004000
Training Epoch: 3 [6400/54000]	Loss: 0.0102	LR: 0.004000
Training Epoch: 3 [6656/54000]	Loss: 0.0354	LR: 0.004000
Training Epoch: 3 [6912/54000]	Loss: 0.0226	LR: 0.004000
Training Epoch: 3 [7168/54000]	Loss: 0.0331	LR: 0.004000
Training Epoch: 3 [7424/54000]	Loss: 0.0173	LR: 0.004000
Training Epoch: 3 [7680/54000]	Loss: 0.0125	LR: 0.004000
Training Epoch: 3 [7936/54000]	Loss: 0.0183	LR: 0.004000
Training Epoch: 3 [8192/54000]	Loss: 0.0365	LR: 0.004000
Training Epoch: 3 [8448/54000]	Loss: 0.0163	LR: 0.004000
Training Epoch: 3 [8704/54000]	Loss: 0.0212	LR: 0.004000
Training Epoch: 3 [8960/54000]	Loss: 0.0186	LR: 0.004000
Training Epoch: 3 [9216/54000]	Loss: 0.0133	LR: 0.004000
Training Epoch: 3 [9472/54000]	Loss: 0.0400	LR: 0.004000
Training Epoch: 3 [9728/54000]	Loss: 0.0298	LR: 0.004000
Training Epoch: 3 [9984/54000]	Loss: 0.0247	LR: 0.004000
Training Epoch: 3 [10240/54000]	Loss: 0.0286	LR: 0.004000
Training Epoch: 3 [10496/54000]	Loss: 0.0269	LR: 0.004000
Training Epoch: 3 [10752/54000]	Loss: 0.0301	LR: 0.004000
Training Epoch: 3 [11008/54000]	Loss: 0.0152	LR: 0.004000
Training Epoch: 3 [11264/54000]	Loss: 0.0205	LR: 0.004000
Training Epoch: 3 [11520/54000]	Loss: 0.0347	LR: 0.004000
Training Epoch: 3 [11776/54000]	Loss: 0.0080	LR: 0.004000
Training Epoch: 3 [12032/54000]	Loss: 0.0198	LR: 0.004000
Training Epoch: 3 [12288/54000]	Loss: 0.0221	LR: 0.004000
Training Epoch: 3 [12544/54000]	Loss: 0.0228	LR: 0.004000
Training Epoch: 3 [12800/54000]	Loss: 0.0265	LR: 0.004000
Training Epoch: 3 [13056/54000]	Loss: 0.0152	LR: 0.004000
Training Epoch: 3 [13312/54000]	Loss: 0.0326	LR: 0.004000
Training Epoch: 3 [13568/54000]	Loss: 0.0469	LR: 0.004000
Training Epoch: 3 [13824/54000]	Loss: 0.0236	LR: 0.004000
Training Epoch: 3 [14080/54000]	Loss: 0.0169	LR: 0.004000
Training Epoch: 3 [14336/54000]	Loss: 0.0222	LR: 0.004000
Training Epoch: 3 [14592/54000]	Loss: 0.0292	LR: 0.004000
Training Epoch: 3 [14848/54000]	Loss: 0.0390	LR: 0.004000
Training Epoch: 3 [15104/54000]	Loss: 0.0453	LR: 0.004000
Training Epoch: 3 [15360/54000]	Loss: 0.0350	LR: 0.004000
Training Epoch: 3 [15616/54000]	Loss: 0.0542	LR: 0.004000
Training Epoch: 3 [15872/54000]	Loss: 0.0444	LR: 0.004000
Training Epoch: 3 [16128/54000]	Loss: 0.0312	LR: 0.004000
Training Epoch: 3 [16384/54000]	Loss: 0.0181	LR: 0.004000
Training Epoch: 3 [16640/54000]	Loss: 0.0186	LR: 0.004000
Training Epoch: 3 [16896/54000]	Loss: 0.0113	LR: 0.004000
Training Epoch: 3 [17152/54000]	Loss: 0.0290	LR: 0.004000
Training Epoch: 3 [17408/54000]	Loss: 0.0087	LR: 0.004000
Training Epoch: 3 [17664/54000]	Loss: 0.0301	LR: 0.004000
Training Epoch: 3 [17920/54000]	Loss: 0.0450	LR: 0.004000
Training Epoch: 3 [18176/54000]	Loss: 0.0297	LR: 0.004000
Training Epoch: 3 [18432/54000]	Loss: 0.0250	LR: 0.004000
Training Epoch: 3 [18688/54000]	Loss: 0.0144	LR: 0.004000
Training Epoch: 3 [18944/54000]	Loss: 0.0288	LR: 0.004000
Training Epoch: 3 [19200/54000]	Loss: 0.0136	LR: 0.004000
Training Epoch: 3 [19456/54000]	Loss: 0.0150	LR: 0.004000
Training Epoch: 3 [19712/54000]	Loss: 0.0099	LR: 0.004000
Training Epoch: 3 [19968/54000]	Loss: 0.0231	LR: 0.004000
Training Epoch: 3 [20224/54000]	Loss: 0.0145	LR: 0.004000
Training Epoch: 3 [20480/54000]	Loss: 0.0165	LR: 0.004000
Training Epoch: 3 [20736/54000]	Loss: 0.0358	LR: 0.004000
Training Epoch: 3 [20992/54000]	Loss: 0.0334	LR: 0.004000
Training Epoch: 3 [21248/54000]	Loss: 0.0165	LR: 0.004000
Training Epoch: 3 [21504/54000]	Loss: 0.0283	LR: 0.004000
Training Epoch: 3 [21760/54000]	Loss: 0.0155	LR: 0.004000
Training Epoch: 3 [22016/54000]	Loss: 0.0270	LR: 0.004000
Training Epoch: 3 [22272/54000]	Loss: 0.0210	LR: 0.004000
Training Epoch: 3 [22528/54000]	Loss: 0.0073	LR: 0.004000
Training Epoch: 3 [22784/54000]	Loss: 0.0260	LR: 0.004000
Training Epoch: 3 [23040/54000]	Loss: 0.0232	LR: 0.004000
Training Epoch: 3 [23296/54000]	Loss: 0.0202	LR: 0.004000
Training Epoch: 3 [23552/54000]	Loss: 0.0255	LR: 0.004000
Training Epoch: 3 [23808/54000]	Loss: 0.0357	LR: 0.004000
Training Epoch: 3 [24064/54000]	Loss: 0.0229	LR: 0.004000
Training Epoch: 3 [24320/54000]	Loss: 0.0059	LR: 0.004000
Training Epoch: 3 [24576/54000]	Loss: 0.0104	LR: 0.004000
Training Epoch: 3 [24832/54000]	Loss: 0.0342	LR: 0.004000
Training Epoch: 3 [25088/54000]	Loss: 0.0219	LR: 0.004000
Training Epoch: 3 [25344/54000]	Loss: 0.0307	LR: 0.004000
Training Epoch: 3 [25600/54000]	Loss: 0.0191	LR: 0.004000
Training Epoch: 3 [25856/54000]	Loss: 0.0190	LR: 0.004000
Training Epoch: 3 [26112/54000]	Loss: 0.0098	LR: 0.004000
Training Epoch: 3 [26368/54000]	Loss: 0.0416	LR: 0.004000
Training Epoch: 3 [26624/54000]	Loss: 0.0282	LR: 0.004000
Training Epoch: 3 [26880/54000]	Loss: 0.0196	LR: 0.004000
Training Epoch: 3 [27136/54000]	Loss: 0.0254	LR: 0.004000
Training Epoch: 3 [27392/54000]	Loss: 0.0267	LR: 0.004000
Training Epoch: 3 [27648/54000]	Loss: 0.0251	LR: 0.004000
Training Epoch: 3 [27904/54000]	Loss: 0.0253	LR: 0.004000
Training Epoch: 3 [28160/54000]	Loss: 0.0237	LR: 0.004000
Training Epoch: 3 [28416/54000]	Loss: 0.0157	LR: 0.004000
Training Epoch: 3 [28672/54000]	Loss: 0.0404	LR: 0.004000
Training Epoch: 3 [28928/54000]	Loss: 0.0203	LR: 0.004000
Training Epoch: 3 [29184/54000]	Loss: 0.0247	LR: 0.004000
Training Epoch: 3 [29440/54000]	Loss: 0.0292	LR: 0.004000
Training Epoch: 3 [29696/54000]	Loss: 0.0135	LR: 0.004000
Training Epoch: 3 [29952/54000]	Loss: 0.0142	LR: 0.004000
Training Epoch: 3 [30208/54000]	Loss: 0.0269	LR: 0.004000
Training Epoch: 3 [30464/54000]	Loss: 0.0278	LR: 0.004000
Training Epoch: 3 [30720/54000]	Loss: 0.0146	LR: 0.004000
Training Epoch: 3 [30976/54000]	Loss: 0.0222	LR: 0.004000
Training Epoch: 3 [31232/54000]	Loss: 0.0468	LR: 0.004000
Training Epoch: 3 [31488/54000]	Loss: 0.0428	LR: 0.004000
Training Epoch: 3 [31744/54000]	Loss: 0.0190	LR: 0.004000
Training Epoch: 3 [32000/54000]	Loss: 0.0419	LR: 0.004000
Training Epoch: 3 [32256/54000]	Loss: 0.0571	LR: 0.004000
Training Epoch: 3 [32512/54000]	Loss: 0.0364	LR: 0.004000
Training Epoch: 3 [32768/54000]	Loss: 0.0257	LR: 0.004000
Training Epoch: 3 [33024/54000]	Loss: 0.0389	LR: 0.004000
Training Epoch: 3 [33280/54000]	Loss: 0.0151	LR: 0.004000
Training Epoch: 3 [33536/54000]	Loss: 0.0058	LR: 0.004000
Training Epoch: 3 [33792/54000]	Loss: 0.0216	LR: 0.004000
Training Epoch: 3 [34048/54000]	Loss: 0.0269	LR: 0.004000
Training Epoch: 3 [34304/54000]	Loss: 0.0376	LR: 0.004000
Training Epoch: 3 [34560/54000]	Loss: 0.0215	LR: 0.004000
Training Epoch: 3 [34816/54000]	Loss: 0.0371	LR: 0.004000
Training Epoch: 3 [35072/54000]	Loss: 0.0620	LR: 0.004000
Training Epoch: 3 [35328/54000]	Loss: 0.0231	LR: 0.004000
Training Epoch: 3 [35584/54000]	Loss: 0.0386	LR: 0.004000
Training Epoch: 3 [35840/54000]	Loss: 0.0321	LR: 0.004000
Training Epoch: 3 [36096/54000]	Loss: 0.0446	LR: 0.004000
Training Epoch: 3 [36352/54000]	Loss: 0.0195	LR: 0.004000
Training Epoch: 3 [36608/54000]	Loss: 0.0192	LR: 0.004000
Training Epoch: 3 [36864/54000]	Loss: 0.0054	LR: 0.004000
Training Epoch: 3 [37120/54000]	Loss: 0.0150	LR: 0.004000
Training Epoch: 3 [37376/54000]	Loss: 0.0214	LR: 0.004000
Training Epoch: 3 [37632/54000]	Loss: 0.0132	LR: 0.004000
Training Epoch: 3 [37888/54000]	Loss: 0.0101	LR: 0.004000
Training Epoch: 3 [38144/54000]	Loss: 0.0291	LR: 0.004000
Training Epoch: 3 [38400/54000]	Loss: 0.0468	LR: 0.004000
Training Epoch: 3 [38656/54000]	Loss: 0.0242	LR: 0.004000
Training Epoch: 3 [38912/54000]	Loss: 0.0136	LR: 0.004000
Training Epoch: 3 [39168/54000]	Loss: 0.0250	LR: 0.004000
Training Epoch: 3 [39424/54000]	Loss: 0.0284	LR: 0.004000
Training Epoch: 3 [39680/54000]	Loss: 0.0273	LR: 0.004000
Training Epoch: 3 [39936/54000]	Loss: 0.0403	LR: 0.004000
Training Epoch: 3 [40192/54000]	Loss: 0.0238	LR: 0.004000
Training Epoch: 3 [40448/54000]	Loss: 0.0488	LR: 0.004000
Training Epoch: 3 [40704/54000]	Loss: 0.0203	LR: 0.004000
Training Epoch: 3 [40960/54000]	Loss: 0.0175	LR: 0.004000
Training Epoch: 3 [41216/54000]	Loss: 0.0192	LR: 0.004000
Training Epoch: 3 [41472/54000]	Loss: 0.0234	LR: 0.004000
Training Epoch: 3 [41728/54000]	Loss: 0.0214	LR: 0.004000
Training Epoch: 3 [41984/54000]	Loss: 0.0279	LR: 0.004000
Training Epoch: 3 [42240/54000]	Loss: 0.0204	LR: 0.004000
Training Epoch: 3 [42496/54000]	Loss: 0.0305	LR: 0.004000
Training Epoch: 3 [42752/54000]	Loss: 0.0421	LR: 0.004000
Training Epoch: 3 [43008/54000]	Loss: 0.0151	LR: 0.004000
Training Epoch: 3 [43264/54000]	Loss: 0.0114	LR: 0.004000
Training Epoch: 3 [43520/54000]	Loss: 0.0548	LR: 0.004000
Training Epoch: 3 [43776/54000]	Loss: 0.0292	LR: 0.004000
Training Epoch: 3 [44032/54000]	Loss: 0.0188	LR: 0.004000
Training Epoch: 3 [44288/54000]	Loss: 0.0136	LR: 0.004000
Training Epoch: 3 [44544/54000]	Loss: 0.0127	LR: 0.004000
Training Epoch: 3 [44800/54000]	Loss: 0.0323	LR: 0.004000
Training Epoch: 3 [45056/54000]	Loss: 0.0154	LR: 0.004000
Training Epoch: 3 [45312/54000]	Loss: 0.0168	LR: 0.004000
Training Epoch: 3 [45568/54000]	Loss: 0.0400	LR: 0.004000
Training Epoch: 3 [45824/54000]	Loss: 0.0566	LR: 0.004000
Training Epoch: 3 [46080/54000]	Loss: 0.0221	LR: 0.004000
Training Epoch: 3 [46336/54000]	Loss: 0.0314	LR: 0.004000
Training Epoch: 3 [46592/54000]	Loss: 0.0174	LR: 0.004000
Training Epoch: 3 [46848/54000]	Loss: 0.0341	LR: 0.004000
Training Epoch: 3 [47104/54000]	Loss: 0.0144	LR: 0.004000
Training Epoch: 3 [47360/54000]	Loss: 0.0333	LR: 0.004000
Training Epoch: 3 [47616/54000]	Loss: 0.0197	LR: 0.004000
Training Epoch: 3 [47872/54000]	Loss: 0.0397	LR: 0.004000
Training Epoch: 3 [48128/54000]	Loss: 0.0227	LR: 0.004000
Training Epoch: 3 [48384/54000]	Loss: 0.0107	LR: 0.004000
Training Epoch: 3 [48640/54000]	Loss: 0.0247	LR: 0.004000
Training Epoch: 3 [48896/54000]	Loss: 0.0122	LR: 0.004000
Training Epoch: 3 [49152/54000]	Loss: 0.0285	LR: 0.004000
Training Epoch: 3 [49408/54000]	Loss: 0.0207	LR: 0.004000
Training Epoch: 3 [49664/54000]	Loss: 0.0327	LR: 0.004000
Training Epoch: 3 [49920/54000]	Loss: 0.0385	LR: 0.004000
Training Epoch: 3 [50176/54000]	Loss: 0.0191	LR: 0.004000
Training Epoch: 3 [50432/54000]	Loss: 0.0380	LR: 0.004000
Training Epoch: 3 [50688/54000]	Loss: 0.0108	LR: 0.004000
Training Epoch: 3 [50944/54000]	Loss: 0.0417	LR: 0.004000
Training Epoch: 3 [51200/54000]	Loss: 0.0192	LR: 0.004000
Training Epoch: 3 [51456/54000]	Loss: 0.0134	LR: 0.004000
Training Epoch: 3 [51712/54000]	Loss: 0.0177	LR: 0.004000
Training Epoch: 3 [51968/54000]	Loss: 0.0126	LR: 0.004000
Training Epoch: 3 [52224/54000]	Loss: 0.0331	LR: 0.004000
Training Epoch: 3 [52480/54000]	Loss: 0.0247	LR: 0.004000
Training Epoch: 3 [52736/54000]	Loss: 0.0264	LR: 0.004000
Training Epoch: 3 [52992/54000]	Loss: 0.0408	LR: 0.004000
Training Epoch: 3 [53248/54000]	Loss: 0.0138	LR: 0.004000
Training Epoch: 3 [53504/54000]	Loss: 0.0478	LR: 0.004000
Training Epoch: 3 [53760/54000]	Loss: 0.0263	LR: 0.004000
Training Epoch: 3 [54000/54000]	Loss: 0.0595	LR: 0.004000
Epoch 3 - Average Train Loss: 0.0264, Train Accuracy: 0.9926
Epoch 3 training time consumed: 38.15s
Evaluating Network.....
Test set: Epoch: 3, Average loss: 0.0001, Accuracy: 0.9948, Time consumed:1.61s
Saving weights file to checkpoint/retrain/AllCNN/Wednesday_23_July_2025_06h_24m_42s/AllCNN-Mnist-seed1-ret100-3-best.pth
Training Epoch: 4 [256/54000]	Loss: 0.0228	LR: 0.000800
Training Epoch: 4 [512/54000]	Loss: 0.0397	LR: 0.000800
Training Epoch: 4 [768/54000]	Loss: 0.0153	LR: 0.000800
Training Epoch: 4 [1024/54000]	Loss: 0.0458	LR: 0.000800
Training Epoch: 4 [1280/54000]	Loss: 0.0255	LR: 0.000800
Training Epoch: 4 [1536/54000]	Loss: 0.0354	LR: 0.000800
Training Epoch: 4 [1792/54000]	Loss: 0.0138	LR: 0.000800
Training Epoch: 4 [2048/54000]	Loss: 0.0407	LR: 0.000800
Training Epoch: 4 [2304/54000]	Loss: 0.0206	LR: 0.000800
Training Epoch: 4 [2560/54000]	Loss: 0.0128	LR: 0.000800
Training Epoch: 4 [2816/54000]	Loss: 0.0079	LR: 0.000800
Training Epoch: 4 [3072/54000]	Loss: 0.0224	LR: 0.000800
Training Epoch: 4 [3328/54000]	Loss: 0.0155	LR: 0.000800
Training Epoch: 4 [3584/54000]	Loss: 0.0226	LR: 0.000800
Training Epoch: 4 [3840/54000]	Loss: 0.0065	LR: 0.000800
Training Epoch: 4 [4096/54000]	Loss: 0.0066	LR: 0.000800
Training Epoch: 4 [4352/54000]	Loss: 0.0203	LR: 0.000800
Training Epoch: 4 [4608/54000]	Loss: 0.0358	LR: 0.000800
Training Epoch: 4 [4864/54000]	Loss: 0.0279	LR: 0.000800
Training Epoch: 4 [5120/54000]	Loss: 0.0179	LR: 0.000800
Training Epoch: 4 [5376/54000]	Loss: 0.0236	LR: 0.000800
Training Epoch: 4 [5632/54000]	Loss: 0.0422	LR: 0.000800
Training Epoch: 4 [5888/54000]	Loss: 0.0501	LR: 0.000800
Training Epoch: 4 [6144/54000]	Loss: 0.0200	LR: 0.000800
Training Epoch: 4 [6400/54000]	Loss: 0.0242	LR: 0.000800
Training Epoch: 4 [6656/54000]	Loss: 0.0096	LR: 0.000800
Training Epoch: 4 [6912/54000]	Loss: 0.0144	LR: 0.000800
Training Epoch: 4 [7168/54000]	Loss: 0.0146	LR: 0.000800
Training Epoch: 4 [7424/54000]	Loss: 0.0260	LR: 0.000800
Training Epoch: 4 [7680/54000]	Loss: 0.0289	LR: 0.000800
Training Epoch: 4 [7936/54000]	Loss: 0.0270	LR: 0.000800
Training Epoch: 4 [8192/54000]	Loss: 0.0483	LR: 0.000800
Training Epoch: 4 [8448/54000]	Loss: 0.0150	LR: 0.000800
Training Epoch: 4 [8704/54000]	Loss: 0.0125	LR: 0.000800
Training Epoch: 4 [8960/54000]	Loss: 0.0094	LR: 0.000800
Training Epoch: 4 [9216/54000]	Loss: 0.0195	LR: 0.000800
Training Epoch: 4 [9472/54000]	Loss: 0.0206	LR: 0.000800
Training Epoch: 4 [9728/54000]	Loss: 0.0142	LR: 0.000800
Training Epoch: 4 [9984/54000]	Loss: 0.0317	LR: 0.000800
Training Epoch: 4 [10240/54000]	Loss: 0.0194	LR: 0.000800
Training Epoch: 4 [10496/54000]	Loss: 0.0292	LR: 0.000800
Training Epoch: 4 [10752/54000]	Loss: 0.0230	LR: 0.000800
Training Epoch: 4 [11008/54000]	Loss: 0.0227	LR: 0.000800
Training Epoch: 4 [11264/54000]	Loss: 0.0507	LR: 0.000800
Training Epoch: 4 [11520/54000]	Loss: 0.0186	LR: 0.000800
Training Epoch: 4 [11776/54000]	Loss: 0.0118	LR: 0.000800
Training Epoch: 4 [12032/54000]	Loss: 0.0289	LR: 0.000800
Training Epoch: 4 [12288/54000]	Loss: 0.0495	LR: 0.000800
Training Epoch: 4 [12544/54000]	Loss: 0.0206	LR: 0.000800
Training Epoch: 4 [12800/54000]	Loss: 0.0191	LR: 0.000800
Training Epoch: 4 [13056/54000]	Loss: 0.0270	LR: 0.000800
Training Epoch: 4 [13312/54000]	Loss: 0.0473	LR: 0.000800
Training Epoch: 4 [13568/54000]	Loss: 0.0253	LR: 0.000800
Training Epoch: 4 [13824/54000]	Loss: 0.0163	LR: 0.000800
Training Epoch: 4 [14080/54000]	Loss: 0.0084	LR: 0.000800
Training Epoch: 4 [14336/54000]	Loss: 0.0207	LR: 0.000800
Training Epoch: 4 [14592/54000]	Loss: 0.0428	LR: 0.000800
Training Epoch: 4 [14848/54000]	Loss: 0.0328	LR: 0.000800
Training Epoch: 4 [15104/54000]	Loss: 0.0353	LR: 0.000800
Training Epoch: 4 [15360/54000]	Loss: 0.0298	LR: 0.000800
Training Epoch: 4 [15616/54000]	Loss: 0.0214	LR: 0.000800
Training Epoch: 4 [15872/54000]	Loss: 0.0175	LR: 0.000800
Training Epoch: 4 [16128/54000]	Loss: 0.0160	LR: 0.000800
Training Epoch: 4 [16384/54000]	Loss: 0.0138	LR: 0.000800
Training Epoch: 4 [16640/54000]	Loss: 0.0186	LR: 0.000800
Training Epoch: 4 [16896/54000]	Loss: 0.0318	LR: 0.000800
Training Epoch: 4 [17152/54000]	Loss: 0.0110	LR: 0.000800
Training Epoch: 4 [17408/54000]	Loss: 0.0344	LR: 0.000800
Training Epoch: 4 [17664/54000]	Loss: 0.0322	LR: 0.000800
Training Epoch: 4 [17920/54000]	Loss: 0.0207	LR: 0.000800
Training Epoch: 4 [18176/54000]	Loss: 0.0165	LR: 0.000800
Training Epoch: 4 [18432/54000]	Loss: 0.0187	LR: 0.000800
Training Epoch: 4 [18688/54000]	Loss: 0.0357	LR: 0.000800
Training Epoch: 4 [18944/54000]	Loss: 0.0205	LR: 0.000800
Training Epoch: 4 [19200/54000]	Loss: 0.0247	LR: 0.000800
Training Epoch: 4 [19456/54000]	Loss: 0.0093	LR: 0.000800
Training Epoch: 4 [19712/54000]	Loss: 0.0227	LR: 0.000800
Training Epoch: 4 [19968/54000]	Loss: 0.0195	LR: 0.000800
Training Epoch: 4 [20224/54000]	Loss: 0.0214	LR: 0.000800
Training Epoch: 4 [20480/54000]	Loss: 0.0219	LR: 0.000800
Training Epoch: 4 [20736/54000]	Loss: 0.0218	LR: 0.000800
Training Epoch: 4 [20992/54000]	Loss: 0.0236	LR: 0.000800
Training Epoch: 4 [21248/54000]	Loss: 0.0249	LR: 0.000800
Training Epoch: 4 [21504/54000]	Loss: 0.0312	LR: 0.000800
Training Epoch: 4 [21760/54000]	Loss: 0.0127	LR: 0.000800
Training Epoch: 4 [22016/54000]	Loss: 0.0178	LR: 0.000800
Training Epoch: 4 [22272/54000]	Loss: 0.0266	LR: 0.000800
Training Epoch: 4 [22528/54000]	Loss: 0.0315	LR: 0.000800
Training Epoch: 4 [22784/54000]	Loss: 0.0245	LR: 0.000800
Training Epoch: 4 [23040/54000]	Loss: 0.0296	LR: 0.000800
Training Epoch: 4 [23296/54000]	Loss: 0.0093	LR: 0.000800
Training Epoch: 4 [23552/54000]	Loss: 0.0232	LR: 0.000800
Training Epoch: 4 [23808/54000]	Loss: 0.0080	LR: 0.000800
Training Epoch: 4 [24064/54000]	Loss: 0.0133	LR: 0.000800
Training Epoch: 4 [24320/54000]	Loss: 0.0106	LR: 0.000800
Training Epoch: 4 [24576/54000]	Loss: 0.0303	LR: 0.000800
Training Epoch: 4 [24832/54000]	Loss: 0.0538	LR: 0.000800
Training Epoch: 4 [25088/54000]	Loss: 0.0184	LR: 0.000800
Training Epoch: 4 [25344/54000]	Loss: 0.0316	LR: 0.000800
Training Epoch: 4 [25600/54000]	Loss: 0.0178	LR: 0.000800
Training Epoch: 4 [25856/54000]	Loss: 0.0134	LR: 0.000800
Training Epoch: 4 [26112/54000]	Loss: 0.0485	LR: 0.000800
Training Epoch: 4 [26368/54000]	Loss: 0.0278	LR: 0.000800
Training Epoch: 4 [26624/54000]	Loss: 0.0237	LR: 0.000800
Training Epoch: 4 [26880/54000]	Loss: 0.0158	LR: 0.000800
Training Epoch: 4 [27136/54000]	Loss: 0.0102	LR: 0.000800
Training Epoch: 4 [27392/54000]	Loss: 0.0502	LR: 0.000800
Training Epoch: 4 [27648/54000]	Loss: 0.0254	LR: 0.000800
Training Epoch: 4 [27904/54000]	Loss: 0.0378	LR: 0.000800
Training Epoch: 4 [28160/54000]	Loss: 0.0156	LR: 0.000800
Training Epoch: 4 [28416/54000]	Loss: 0.0110	LR: 0.000800
Training Epoch: 4 [28672/54000]	Loss: 0.0269	LR: 0.000800
Training Epoch: 4 [28928/54000]	Loss: 0.0101	LR: 0.000800
Training Epoch: 4 [29184/54000]	Loss: 0.0141	LR: 0.000800
Training Epoch: 4 [29440/54000]	Loss: 0.0179	LR: 0.000800
Training Epoch: 4 [29696/54000]	Loss: 0.0216	LR: 0.000800
Training Epoch: 4 [29952/54000]	Loss: 0.0107	LR: 0.000800
Training Epoch: 4 [30208/54000]	Loss: 0.0101	LR: 0.000800
Training Epoch: 4 [30464/54000]	Loss: 0.0316	LR: 0.000800
Training Epoch: 4 [30720/54000]	Loss: 0.0232	LR: 0.000800
Training Epoch: 4 [30976/54000]	Loss: 0.0302	LR: 0.000800
Training Epoch: 4 [31232/54000]	Loss: 0.0135	LR: 0.000800
Training Epoch: 4 [31488/54000]	Loss: 0.0146	LR: 0.000800
Training Epoch: 4 [31744/54000]	Loss: 0.0186	LR: 0.000800
Training Epoch: 4 [32000/54000]	Loss: 0.0273	LR: 0.000800
Training Epoch: 4 [32256/54000]	Loss: 0.0342	LR: 0.000800
Training Epoch: 4 [32512/54000]	Loss: 0.0300	LR: 0.000800
Training Epoch: 4 [32768/54000]	Loss: 0.0115	LR: 0.000800
Training Epoch: 4 [33024/54000]	Loss: 0.0248	LR: 0.000800
Training Epoch: 4 [33280/54000]	Loss: 0.0245	LR: 0.000800
Training Epoch: 4 [33536/54000]	Loss: 0.0139	LR: 0.000800
Training Epoch: 4 [33792/54000]	Loss: 0.0407	LR: 0.000800
Training Epoch: 4 [34048/54000]	Loss: 0.0187	LR: 0.000800
Training Epoch: 4 [34304/54000]	Loss: 0.0123	LR: 0.000800
Training Epoch: 4 [34560/54000]	Loss: 0.0241	LR: 0.000800
Training Epoch: 4 [34816/54000]	Loss: 0.0130	LR: 0.000800
Training Epoch: 4 [35072/54000]	Loss: 0.0469	LR: 0.000800
Training Epoch: 4 [35328/54000]	Loss: 0.0246	LR: 0.000800
Training Epoch: 4 [35584/54000]	Loss: 0.0271	LR: 0.000800
Training Epoch: 4 [35840/54000]	Loss: 0.0194	LR: 0.000800
Training Epoch: 4 [36096/54000]	Loss: 0.0078	LR: 0.000800
Training Epoch: 4 [36352/54000]	Loss: 0.0243	LR: 0.000800
Training Epoch: 4 [36608/54000]	Loss: 0.0260	LR: 0.000800
Training Epoch: 4 [36864/54000]	Loss: 0.0148	LR: 0.000800
Training Epoch: 4 [37120/54000]	Loss: 0.0263	LR: 0.000800
Training Epoch: 4 [37376/54000]	Loss: 0.0162	LR: 0.000800
Training Epoch: 4 [37632/54000]	Loss: 0.0264	LR: 0.000800
Training Epoch: 4 [37888/54000]	Loss: 0.0217	LR: 0.000800
Training Epoch: 4 [38144/54000]	Loss: 0.0214	LR: 0.000800
Training Epoch: 4 [38400/54000]	Loss: 0.0207	LR: 0.000800
Training Epoch: 4 [38656/54000]	Loss: 0.0284	LR: 0.000800
Training Epoch: 4 [38912/54000]	Loss: 0.0133	LR: 0.000800
Training Epoch: 4 [39168/54000]	Loss: 0.0174	LR: 0.000800
Training Epoch: 4 [39424/54000]	Loss: 0.0211	LR: 0.000800
Training Epoch: 4 [39680/54000]	Loss: 0.0403	LR: 0.000800
Training Epoch: 4 [39936/54000]	Loss: 0.0108	LR: 0.000800
Training Epoch: 4 [40192/54000]	Loss: 0.0223	LR: 0.000800
Training Epoch: 4 [40448/54000]	Loss: 0.0321	LR: 0.000800
Training Epoch: 4 [40704/54000]	Loss: 0.0201	LR: 0.000800
Training Epoch: 4 [40960/54000]	Loss: 0.0495	LR: 0.000800
Training Epoch: 4 [41216/54000]	Loss: 0.0098	LR: 0.000800
Training Epoch: 4 [41472/54000]	Loss: 0.0384	LR: 0.000800
Training Epoch: 4 [41728/54000]	Loss: 0.0068	LR: 0.000800
Training Epoch: 4 [41984/54000]	Loss: 0.0239	LR: 0.000800
Training Epoch: 4 [42240/54000]	Loss: 0.0261	LR: 0.000800
Training Epoch: 4 [42496/54000]	Loss: 0.0081	LR: 0.000800
Training Epoch: 4 [42752/54000]	Loss: 0.0185	LR: 0.000800
Training Epoch: 4 [43008/54000]	Loss: 0.0205	LR: 0.000800
Training Epoch: 4 [43264/54000]	Loss: 0.0096	LR: 0.000800
Training Epoch: 4 [43520/54000]	Loss: 0.0228	LR: 0.000800
Training Epoch: 4 [43776/54000]	Loss: 0.0118	LR: 0.000800
Training Epoch: 4 [44032/54000]	Loss: 0.0342	LR: 0.000800
Training Epoch: 4 [44288/54000]	Loss: 0.0174	LR: 0.000800
Training Epoch: 4 [44544/54000]	Loss: 0.0143	LR: 0.000800
Training Epoch: 4 [44800/54000]	Loss: 0.0134	LR: 0.000800
Training Epoch: 4 [45056/54000]	Loss: 0.0147	LR: 0.000800
Training Epoch: 4 [45312/54000]	Loss: 0.0162	LR: 0.000800
Training Epoch: 4 [45568/54000]	Loss: 0.0135	LR: 0.000800
Training Epoch: 4 [45824/54000]	Loss: 0.0140	LR: 0.000800
Training Epoch: 4 [46080/54000]	Loss: 0.0072	LR: 0.000800
Training Epoch: 4 [46336/54000]	Loss: 0.0467	LR: 0.000800
Training Epoch: 4 [46592/54000]	Loss: 0.0068	LR: 0.000800
Training Epoch: 4 [46848/54000]	Loss: 0.0088	LR: 0.000800
Training Epoch: 4 [47104/54000]	Loss: 0.0146	LR: 0.000800
Training Epoch: 4 [47360/54000]	Loss: 0.0253	LR: 0.000800
Training Epoch: 4 [47616/54000]	Loss: 0.0224	LR: 0.000800
Training Epoch: 4 [47872/54000]	Loss: 0.0367	LR: 0.000800
Training Epoch: 4 [48128/54000]	Loss: 0.0146	LR: 0.000800
Training Epoch: 4 [48384/54000]	Loss: 0.0219	LR: 0.000800
Training Epoch: 4 [48640/54000]	Loss: 0.0320	LR: 0.000800
Training Epoch: 4 [48896/54000]	Loss: 0.0479	LR: 0.000800
Training Epoch: 4 [49152/54000]	Loss: 0.0302	LR: 0.000800
Training Epoch: 4 [49408/54000]	Loss: 0.0184	LR: 0.000800
Training Epoch: 4 [49664/54000]	Loss: 0.0549	LR: 0.000800
Training Epoch: 4 [49920/54000]	Loss: 0.0256	LR: 0.000800
Training Epoch: 4 [50176/54000]	Loss: 0.0164	LR: 0.000800
Training Epoch: 4 [50432/54000]	Loss: 0.0173	LR: 0.000800
Training Epoch: 4 [50688/54000]	Loss: 0.0356	LR: 0.000800
Training Epoch: 4 [50944/54000]	Loss: 0.0164	LR: 0.000800
Training Epoch: 4 [51200/54000]	Loss: 0.0336	LR: 0.000800
Training Epoch: 4 [51456/54000]	Loss: 0.0352	LR: 0.000800
Training Epoch: 4 [51712/54000]	Loss: 0.0130	LR: 0.000800
Training Epoch: 4 [51968/54000]	Loss: 0.0227	LR: 0.000800
Training Epoch: 4 [52224/54000]	Loss: 0.0477	LR: 0.000800
Training Epoch: 4 [52480/54000]	Loss: 0.0285	LR: 0.000800
Training Epoch: 4 [52736/54000]	Loss: 0.0084	LR: 0.000800
Training Epoch: 4 [52992/54000]	Loss: 0.0123	LR: 0.000800
Training Epoch: 4 [53248/54000]	Loss: 0.0243	LR: 0.000800
Training Epoch: 4 [53504/54000]	Loss: 0.0289	LR: 0.000800
Training Epoch: 4 [53760/54000]	Loss: 0.0189	LR: 0.000800
Training Epoch: 4 [54000/54000]	Loss: 0.0231	LR: 0.000800
Epoch 4 - Average Train Loss: 0.0231, Train Accuracy: 0.9940
Epoch 4 training time consumed: 38.32s
Evaluating Network.....
Test set: Epoch: 4, Average loss: 0.0001, Accuracy: 0.9955, Time consumed:1.58s
Saving weights file to checkpoint/retrain/AllCNN/Wednesday_23_July_2025_06h_24m_42s/AllCNN-Mnist-seed1-ret100-4-best.pth
Training Epoch: 5 [256/54000]	Loss: 0.0166	LR: 0.000800
Training Epoch: 5 [512/54000]	Loss: 0.0284	LR: 0.000800
Training Epoch: 5 [768/54000]	Loss: 0.0293	LR: 0.000800
Training Epoch: 5 [1024/54000]	Loss: 0.0346	LR: 0.000800
Training Epoch: 5 [1280/54000]	Loss: 0.0236	LR: 0.000800
Training Epoch: 5 [1536/54000]	Loss: 0.0277	LR: 0.000800
Training Epoch: 5 [1792/54000]	Loss: 0.0059	LR: 0.000800
Training Epoch: 5 [2048/54000]	Loss: 0.0382	LR: 0.000800
Training Epoch: 5 [2304/54000]	Loss: 0.0206	LR: 0.000800
Training Epoch: 5 [2560/54000]	Loss: 0.0191	LR: 0.000800
Training Epoch: 5 [2816/54000]	Loss: 0.0195	LR: 0.000800
Training Epoch: 5 [3072/54000]	Loss: 0.0140	LR: 0.000800
Training Epoch: 5 [3328/54000]	Loss: 0.0145	LR: 0.000800
Training Epoch: 5 [3584/54000]	Loss: 0.0128	LR: 0.000800
Training Epoch: 5 [3840/54000]	Loss: 0.0190	LR: 0.000800
Training Epoch: 5 [4096/54000]	Loss: 0.0274	LR: 0.000800
Training Epoch: 5 [4352/54000]	Loss: 0.0212	LR: 0.000800
Training Epoch: 5 [4608/54000]	Loss: 0.0245	LR: 0.000800
Training Epoch: 5 [4864/54000]	Loss: 0.0297	LR: 0.000800
Training Epoch: 5 [5120/54000]	Loss: 0.0187	LR: 0.000800
Training Epoch: 5 [5376/54000]	Loss: 0.0274	LR: 0.000800
Training Epoch: 5 [5632/54000]	Loss: 0.0208	LR: 0.000800
Training Epoch: 5 [5888/54000]	Loss: 0.0188	LR: 0.000800
Training Epoch: 5 [6144/54000]	Loss: 0.0214	LR: 0.000800
Training Epoch: 5 [6400/54000]	Loss: 0.0185	LR: 0.000800
Training Epoch: 5 [6656/54000]	Loss: 0.0069	LR: 0.000800
Training Epoch: 5 [6912/54000]	Loss: 0.0139	LR: 0.000800
Training Epoch: 5 [7168/54000]	Loss: 0.0105	LR: 0.000800
Training Epoch: 5 [7424/54000]	Loss: 0.0061	LR: 0.000800
Training Epoch: 5 [7680/54000]	Loss: 0.0359	LR: 0.000800
Training Epoch: 5 [7936/54000]	Loss: 0.0165	LR: 0.000800
Training Epoch: 5 [8192/54000]	Loss: 0.0233	LR: 0.000800
Training Epoch: 5 [8448/54000]	Loss: 0.0377	LR: 0.000800
Training Epoch: 5 [8704/54000]	Loss: 0.0213	LR: 0.000800
Training Epoch: 5 [8960/54000]	Loss: 0.0090	LR: 0.000800
Training Epoch: 5 [9216/54000]	Loss: 0.0357	LR: 0.000800
Training Epoch: 5 [9472/54000]	Loss: 0.0196	LR: 0.000800
Training Epoch: 5 [9728/54000]	Loss: 0.0174	LR: 0.000800
Training Epoch: 5 [9984/54000]	Loss: 0.0401	LR: 0.000800
Training Epoch: 5 [10240/54000]	Loss: 0.0396	LR: 0.000800
Training Epoch: 5 [10496/54000]	Loss: 0.0276	LR: 0.000800
Training Epoch: 5 [10752/54000]	Loss: 0.0315	LR: 0.000800
Training Epoch: 5 [11008/54000]	Loss: 0.0255	LR: 0.000800
Training Epoch: 5 [11264/54000]	Loss: 0.0175	LR: 0.000800
Training Epoch: 5 [11520/54000]	Loss: 0.0272	LR: 0.000800
Training Epoch: 5 [11776/54000]	Loss: 0.0077	LR: 0.000800
Training Epoch: 5 [12032/54000]	Loss: 0.0198	LR: 0.000800
Training Epoch: 5 [12288/54000]	Loss: 0.0184	LR: 0.000800
Training Epoch: 5 [12544/54000]	Loss: 0.0182	LR: 0.000800
Training Epoch: 5 [12800/54000]	Loss: 0.0287	LR: 0.000800
Training Epoch: 5 [13056/54000]	Loss: 0.0106	LR: 0.000800
Training Epoch: 5 [13312/54000]	Loss: 0.0119	LR: 0.000800
Training Epoch: 5 [13568/54000]	Loss: 0.0297	LR: 0.000800
Training Epoch: 5 [13824/54000]	Loss: 0.0286	LR: 0.000800
Training Epoch: 5 [14080/54000]	Loss: 0.0094	LR: 0.000800
Training Epoch: 5 [14336/54000]	Loss: 0.0418	LR: 0.000800
Training Epoch: 5 [14592/54000]	Loss: 0.0182	LR: 0.000800
Training Epoch: 5 [14848/54000]	Loss: 0.0224	LR: 0.000800
Training Epoch: 5 [15104/54000]	Loss: 0.0159	LR: 0.000800
Training Epoch: 5 [15360/54000]	Loss: 0.0206	LR: 0.000800
Training Epoch: 5 [15616/54000]	Loss: 0.0295	LR: 0.000800
Training Epoch: 5 [15872/54000]	Loss: 0.0125	LR: 0.000800
Training Epoch: 5 [16128/54000]	Loss: 0.0352	LR: 0.000800
Training Epoch: 5 [16384/54000]	Loss: 0.0233	LR: 0.000800
Training Epoch: 5 [16640/54000]	Loss: 0.0237	LR: 0.000800
Training Epoch: 5 [16896/54000]	Loss: 0.0310	LR: 0.000800
Training Epoch: 5 [17152/54000]	Loss: 0.0283	LR: 0.000800
Training Epoch: 5 [17408/54000]	Loss: 0.0256	LR: 0.000800
Training Epoch: 5 [17664/54000]	Loss: 0.0127	LR: 0.000800
Training Epoch: 5 [17920/54000]	Loss: 0.0149	LR: 0.000800
Training Epoch: 5 [18176/54000]	Loss: 0.0196	LR: 0.000800
Training Epoch: 5 [18432/54000]	Loss: 0.0237	LR: 0.000800
Training Epoch: 5 [18688/54000]	Loss: 0.0258	LR: 0.000800
Training Epoch: 5 [18944/54000]	Loss: 0.0284	LR: 0.000800
Training Epoch: 5 [19200/54000]	Loss: 0.0238	LR: 0.000800
Training Epoch: 5 [19456/54000]	Loss: 0.0316	LR: 0.000800
Training Epoch: 5 [19712/54000]	Loss: 0.0261	LR: 0.000800
Training Epoch: 5 [19968/54000]	Loss: 0.0111	LR: 0.000800
Training Epoch: 5 [20224/54000]	Loss: 0.0126	LR: 0.000800
Training Epoch: 5 [20480/54000]	Loss: 0.0165	LR: 0.000800
Training Epoch: 5 [20736/54000]	Loss: 0.0153	LR: 0.000800
Training Epoch: 5 [20992/54000]	Loss: 0.0316	LR: 0.000800
Training Epoch: 5 [21248/54000]	Loss: 0.0215	LR: 0.000800
Training Epoch: 5 [21504/54000]	Loss: 0.0330	LR: 0.000800
Training Epoch: 5 [21760/54000]	Loss: 0.0172	LR: 0.000800
Training Epoch: 5 [22016/54000]	Loss: 0.0153	LR: 0.000800
Training Epoch: 5 [22272/54000]	Loss: 0.0194	LR: 0.000800
Training Epoch: 5 [22528/54000]	Loss: 0.0241	LR: 0.000800
Training Epoch: 5 [22784/54000]	Loss: 0.0191	LR: 0.000800
Training Epoch: 5 [23040/54000]	Loss: 0.0157	LR: 0.000800
Training Epoch: 5 [23296/54000]	Loss: 0.0210	LR: 0.000800
Training Epoch: 5 [23552/54000]	Loss: 0.0260	LR: 0.000800
Training Epoch: 5 [23808/54000]	Loss: 0.0113	LR: 0.000800
Training Epoch: 5 [24064/54000]	Loss: 0.0263	LR: 0.000800
Training Epoch: 5 [24320/54000]	Loss: 0.0260	LR: 0.000800
Training Epoch: 5 [24576/54000]	Loss: 0.0153	LR: 0.000800
Training Epoch: 5 [24832/54000]	Loss: 0.0188	LR: 0.000800
Training Epoch: 5 [25088/54000]	Loss: 0.0404	LR: 0.000800
Training Epoch: 5 [25344/54000]	Loss: 0.0363	LR: 0.000800
Training Epoch: 5 [25600/54000]	Loss: 0.0398	LR: 0.000800
Training Epoch: 5 [25856/54000]	Loss: 0.0301	LR: 0.000800
Training Epoch: 5 [26112/54000]	Loss: 0.0396	LR: 0.000800
Training Epoch: 5 [26368/54000]	Loss: 0.0214	LR: 0.000800
Training Epoch: 5 [26624/54000]	Loss: 0.0374	LR: 0.000800
Training Epoch: 5 [26880/54000]	Loss: 0.0147	LR: 0.000800
Training Epoch: 5 [27136/54000]	Loss: 0.0216	LR: 0.000800
Training Epoch: 5 [27392/54000]	Loss: 0.0258	LR: 0.000800
Training Epoch: 5 [27648/54000]	Loss: 0.0153	LR: 0.000800
Training Epoch: 5 [27904/54000]	Loss: 0.0102	LR: 0.000800
Training Epoch: 5 [28160/54000]	Loss: 0.0132	LR: 0.000800
Training Epoch: 5 [28416/54000]	Loss: 0.0118	LR: 0.000800
Training Epoch: 5 [28672/54000]	Loss: 0.0109	LR: 0.000800
Training Epoch: 5 [28928/54000]	Loss: 0.0124	LR: 0.000800
Training Epoch: 5 [29184/54000]	Loss: 0.0417	LR: 0.000800
Training Epoch: 5 [29440/54000]	Loss: 0.0116	LR: 0.000800
Training Epoch: 5 [29696/54000]	Loss: 0.0162	LR: 0.000800
Training Epoch: 5 [29952/54000]	Loss: 0.0113	LR: 0.000800
Training Epoch: 5 [30208/54000]	Loss: 0.0128	LR: 0.000800
Training Epoch: 5 [30464/54000]	Loss: 0.0336	LR: 0.000800
Training Epoch: 5 [30720/54000]	Loss: 0.0080	LR: 0.000800
Training Epoch: 5 [30976/54000]	Loss: 0.0335	LR: 0.000800
Training Epoch: 5 [31232/54000]	Loss: 0.0224	LR: 0.000800
Training Epoch: 5 [31488/54000]	Loss: 0.0304	LR: 0.000800
Training Epoch: 5 [31744/54000]	Loss: 0.0202	LR: 0.000800
Training Epoch: 5 [32000/54000]	Loss: 0.0263	LR: 0.000800
Training Epoch: 5 [32256/54000]	Loss: 0.0173	LR: 0.000800
Training Epoch: 5 [32512/54000]	Loss: 0.0583	LR: 0.000800
Training Epoch: 5 [32768/54000]	Loss: 0.0379	LR: 0.000800
Training Epoch: 5 [33024/54000]	Loss: 0.0437	LR: 0.000800
Training Epoch: 5 [33280/54000]	Loss: 0.0117	LR: 0.000800
Training Epoch: 5 [33536/54000]	Loss: 0.0274	LR: 0.000800
Training Epoch: 5 [33792/54000]	Loss: 0.0205	LR: 0.000800
Training Epoch: 5 [34048/54000]	Loss: 0.0145	LR: 0.000800
Training Epoch: 5 [34304/54000]	Loss: 0.0091	LR: 0.000800
Training Epoch: 5 [34560/54000]	Loss: 0.0156	LR: 0.000800
Training Epoch: 5 [34816/54000]	Loss: 0.0174	LR: 0.000800
Training Epoch: 5 [35072/54000]	Loss: 0.0193	LR: 0.000800
Training Epoch: 5 [35328/54000]	Loss: 0.0094	LR: 0.000800
Training Epoch: 5 [35584/54000]	Loss: 0.0266	LR: 0.000800
Training Epoch: 5 [35840/54000]	Loss: 0.0318	LR: 0.000800
Training Epoch: 5 [36096/54000]	Loss: 0.0360	LR: 0.000800
Training Epoch: 5 [36352/54000]	Loss: 0.0232	LR: 0.000800
Training Epoch: 5 [36608/54000]	Loss: 0.0178	LR: 0.000800
Training Epoch: 5 [36864/54000]	Loss: 0.0439	LR: 0.000800
Training Epoch: 5 [37120/54000]	Loss: 0.0167	LR: 0.000800
Training Epoch: 5 [37376/54000]	Loss: 0.0230	LR: 0.000800
Training Epoch: 5 [37632/54000]	Loss: 0.0136	LR: 0.000800
Training Epoch: 5 [37888/54000]	Loss: 0.0139	LR: 0.000800
Training Epoch: 5 [38144/54000]	Loss: 0.0179	LR: 0.000800
Training Epoch: 5 [38400/54000]	Loss: 0.0224	LR: 0.000800
Training Epoch: 5 [38656/54000]	Loss: 0.0283	LR: 0.000800
Training Epoch: 5 [38912/54000]	Loss: 0.0259	LR: 0.000800
Training Epoch: 5 [39168/54000]	Loss: 0.0312	LR: 0.000800
Training Epoch: 5 [39424/54000]	Loss: 0.0474	LR: 0.000800
Training Epoch: 5 [39680/54000]	Loss: 0.0314	LR: 0.000800
Training Epoch: 5 [39936/54000]	Loss: 0.0252	LR: 0.000800
Training Epoch: 5 [40192/54000]	Loss: 0.0246	LR: 0.000800
Training Epoch: 5 [40448/54000]	Loss: 0.0061	LR: 0.000800
Training Epoch: 5 [40704/54000]	Loss: 0.0269	LR: 0.000800
Training Epoch: 5 [40960/54000]	Loss: 0.0193	LR: 0.000800
Training Epoch: 5 [41216/54000]	Loss: 0.0453	LR: 0.000800
Training Epoch: 5 [41472/54000]	Loss: 0.0052	LR: 0.000800
Training Epoch: 5 [41728/54000]	Loss: 0.0182	LR: 0.000800
Training Epoch: 5 [41984/54000]	Loss: 0.0222	LR: 0.000800
Training Epoch: 5 [42240/54000]	Loss: 0.0092	LR: 0.000800
Training Epoch: 5 [42496/54000]	Loss: 0.0160	LR: 0.000800
Training Epoch: 5 [42752/54000]	Loss: 0.0189	LR: 0.000800
Training Epoch: 5 [43008/54000]	Loss: 0.0148	LR: 0.000800
Training Epoch: 5 [43264/54000]	Loss: 0.0129	LR: 0.000800
Training Epoch: 5 [43520/54000]	Loss: 0.0137	LR: 0.000800
Training Epoch: 5 [43776/54000]	Loss: 0.0206	LR: 0.000800
Training Epoch: 5 [44032/54000]	Loss: 0.0379	LR: 0.000800
Training Epoch: 5 [44288/54000]	Loss: 0.0191	LR: 0.000800
Training Epoch: 5 [44544/54000]	Loss: 0.0210	LR: 0.000800
Training Epoch: 5 [44800/54000]	Loss: 0.0575	LR: 0.000800
Training Epoch: 5 [45056/54000]	Loss: 0.0185	LR: 0.000800
Training Epoch: 5 [45312/54000]	Loss: 0.0402	LR: 0.000800
Training Epoch: 5 [45568/54000]	Loss: 0.0271	LR: 0.000800
Training Epoch: 5 [45824/54000]	Loss: 0.0113	LR: 0.000800
Training Epoch: 5 [46080/54000]	Loss: 0.0307	LR: 0.000800
Training Epoch: 5 [46336/54000]	Loss: 0.0212	LR: 0.000800
Training Epoch: 5 [46592/54000]	Loss: 0.0079	LR: 0.000800
Training Epoch: 5 [46848/54000]	Loss: 0.0236	LR: 0.000800
Training Epoch: 5 [47104/54000]	Loss: 0.0173	LR: 0.000800
Training Epoch: 5 [47360/54000]	Loss: 0.0309	LR: 0.000800
Training Epoch: 5 [47616/54000]	Loss: 0.0072	LR: 0.000800
Training Epoch: 5 [47872/54000]	Loss: 0.0103	LR: 0.000800
Training Epoch: 5 [48128/54000]	Loss: 0.0231	LR: 0.000800
Training Epoch: 5 [48384/54000]	Loss: 0.0312	LR: 0.000800
Training Epoch: 5 [48640/54000]	Loss: 0.0140	LR: 0.000800
Training Epoch: 5 [48896/54000]	Loss: 0.0150	LR: 0.000800
Training Epoch: 5 [49152/54000]	Loss: 0.0128	LR: 0.000800
Training Epoch: 5 [49408/54000]	Loss: 0.0128	LR: 0.000800
Training Epoch: 5 [49664/54000]	Loss: 0.0125	LR: 0.000800
Training Epoch: 5 [49920/54000]	Loss: 0.0291	LR: 0.000800
Training Epoch: 5 [50176/54000]	Loss: 0.0306	LR: 0.000800
Training Epoch: 5 [50432/54000]	Loss: 0.0117	LR: 0.000800
Training Epoch: 5 [50688/54000]	Loss: 0.0249	LR: 0.000800
Training Epoch: 5 [50944/54000]	Loss: 0.0187	LR: 0.000800
Training Epoch: 5 [51200/54000]	Loss: 0.0272	LR: 0.000800
Training Epoch: 5 [51456/54000]	Loss: 0.0214	LR: 0.000800
Training Epoch: 5 [51712/54000]	Loss: 0.0199	LR: 0.000800
Training Epoch: 5 [51968/54000]	Loss: 0.0380	LR: 0.000800
Training Epoch: 5 [52224/54000]	Loss: 0.0176	LR: 0.000800
Training Epoch: 5 [52480/54000]	Loss: 0.0177	LR: 0.000800
Training Epoch: 5 [52736/54000]	Loss: 0.0095	LR: 0.000800
Training Epoch: 5 [52992/54000]	Loss: 0.0371	LR: 0.000800
Training Epoch: 5 [53248/54000]	Loss: 0.0447	LR: 0.000800
Training Epoch: 5 [53504/54000]	Loss: 0.0241	LR: 0.000800
Training Epoch: 5 [53760/54000]	Loss: 0.0197	LR: 0.000800
Training Epoch: 5 [54000/54000]	Loss: 0.0138	LR: 0.000800
Epoch 5 - Average Train Loss: 0.0225, Train Accuracy: 0.9938
Epoch 5 training time consumed: 38.23s
Evaluating Network.....
Test set: Epoch: 5, Average loss: 0.0001, Accuracy: 0.9955, Time consumed:1.68s
Valid (Test) Dl:  10000
Train Dl:  60000
Retain Train Dl:  54000
Forget Train Dl:  6000
Retain Valid Dl:  54000
Forget Valid Dl:  6000
retain_prob Distribution: 10000 samples
test_prob Distribution: 10000 samples
forget_prob Distribution: 6000 samples
Set1 Distribution: 6000 samples
Set2 Distribution: 6000 samples
Set1 Distribution: 6000 samples
Set2 Distribution: 6000 samples
Set1 Distribution: 10000 samples
Set2 Distribution: 10000 samples
Set1 Distribution: 10000 samples
Set2 Distribution: 10000 samples
Test Accuracy: 99.560546875
Retain Accuracy: 99.44818115234375
Zero-Retain Forget (ZRF): 0.8032039403915405
Membership Inference Attack (MIA): 0.18366666666666667
Forget vs Retain Membership Inference Attack (MIA): 0.5354166666666667
Forget vs Test Membership Inference Attack (MIA): 0.5208333333333334
Test vs Retain Membership Inference Attack (MIA): 0.50525
Train vs Test Membership Inference Attack (MIA): 0.49525
Forget Set Accuracy (Df): 99.24665069580078
Method Execution Time: 847.28 seconds
