./data/MUCAC/CelebAMask-HQ/CelebA-HQ-img
./data/MUCAC/CelebAMask-HQ/CelebA-HQ-img

📌 S Retain class distribution for seed 4:
Class 0: 5284
Class 1: 4210

📌 S Forget class distribution for seed 4:
Class 0: 527
Class 1: 527

📊 Updated class distribution:
Retain set:
  Class 0: 5415
  Class 1: 4341
Forget set:
  Class 0: 396
  Class 1: 396
./data/MUCAC/CelebAMask-HQ/CelebA-HQ-img
./data/MUCAC/CelebAMask-HQ/CelebA-HQ-img
⚠️ Warning: Retain train loader may not be shuffled.
Training Epoch: 1 [256/9756]	Loss: 0.8567	LR: 0.000000
Training Epoch: 1 [512/9756]	Loss: 0.8517	LR: 0.002564
Training Epoch: 1 [768/9756]	Loss: 0.7073	LR: 0.005128
Training Epoch: 1 [1024/9756]	Loss: 1.0976	LR: 0.007692
Training Epoch: 1 [1280/9756]	Loss: 1.2975	LR: 0.010256
Training Epoch: 1 [1536/9756]	Loss: 0.7913	LR: 0.012821
Training Epoch: 1 [1792/9756]	Loss: 1.1724	LR: 0.015385
Training Epoch: 1 [2048/9756]	Loss: 1.1440	LR: 0.017949
Training Epoch: 1 [2304/9756]	Loss: 1.0908	LR: 0.020513
Training Epoch: 1 [2560/9756]	Loss: 1.2482	LR: 0.023077
Training Epoch: 1 [2816/9756]	Loss: 0.8843	LR: 0.025641
Training Epoch: 1 [3072/9756]	Loss: 1.0371	LR: 0.028205
Training Epoch: 1 [3328/9756]	Loss: 0.8047	LR: 0.030769
Training Epoch: 1 [3584/9756]	Loss: 0.8939	LR: 0.033333
Training Epoch: 1 [3840/9756]	Loss: 0.8118	LR: 0.035897
Training Epoch: 1 [4096/9756]	Loss: 0.7310	LR: 0.038462
Training Epoch: 1 [4352/9756]	Loss: 0.7793	LR: 0.041026
Training Epoch: 1 [4608/9756]	Loss: 0.6884	LR: 0.043590
Training Epoch: 1 [4864/9756]	Loss: 0.8027	LR: 0.046154
Training Epoch: 1 [5120/9756]	Loss: 0.6974	LR: 0.048718
Training Epoch: 1 [5376/9756]	Loss: 0.8143	LR: 0.051282
Training Epoch: 1 [5632/9756]	Loss: 0.7053	LR: 0.053846
Training Epoch: 1 [5888/9756]	Loss: 0.7459	LR: 0.056410
Training Epoch: 1 [6144/9756]	Loss: 0.7644	LR: 0.058974
Training Epoch: 1 [6400/9756]	Loss: 0.7255	LR: 0.061538
Training Epoch: 1 [6656/9756]	Loss: 0.7151	LR: 0.064103
Training Epoch: 1 [6912/9756]	Loss: 0.6838	LR: 0.066667
Training Epoch: 1 [7168/9756]	Loss: 0.7133	LR: 0.069231
Training Epoch: 1 [7424/9756]	Loss: 0.7107	LR: 0.071795
Training Epoch: 1 [7680/9756]	Loss: 0.7321	LR: 0.074359
Training Epoch: 1 [7936/9756]	Loss: 0.7123	LR: 0.076923
Training Epoch: 1 [8192/9756]	Loss: 0.7355	LR: 0.079487
Training Epoch: 1 [8448/9756]	Loss: 0.7136	LR: 0.082051
Training Epoch: 1 [8704/9756]	Loss: 0.6913	LR: 0.084615
Training Epoch: 1 [8960/9756]	Loss: 0.7474	LR: 0.087179
Training Epoch: 1 [9216/9756]	Loss: 0.7281	LR: 0.089744
Training Epoch: 1 [9472/9756]	Loss: 0.7136	LR: 0.092308
Training Epoch: 1 [9728/9756]	Loss: 0.8146	LR: 0.094872
Training Epoch: 1 [9756/9756]	Loss: 0.7241	LR: 0.097436
Epoch 1 - Average Train Loss: 0.8301, Train Accuracy: 0.5149
Epoch 1 training time consumed: 345.98s
Evaluating Network.....
Test set: Epoch: 1, Average loss: 0.0040, Accuracy: 0.4450, Time consumed:7.97s
Saving weights file to checkpoint/retrain/ResNet18/Saturday_26_July_2025_01h_54m_23s/ResNet18-MUCAC-seed4-ret25-1-best.pth
Training Epoch: 2 [256/9756]	Loss: 0.9666	LR: 0.100000
Training Epoch: 2 [512/9756]	Loss: 0.9382	LR: 0.100000
Training Epoch: 2 [768/9756]	Loss: 0.6808	LR: 0.100000
Training Epoch: 2 [1024/9756]	Loss: 0.7585	LR: 0.100000
Training Epoch: 2 [1280/9756]	Loss: 0.9096	LR: 0.100000
Training Epoch: 2 [1536/9756]	Loss: 0.7796	LR: 0.100000
Training Epoch: 2 [1792/9756]	Loss: 0.7022	LR: 0.100000
Training Epoch: 2 [2048/9756]	Loss: 0.7878	LR: 0.100000
Training Epoch: 2 [2304/9756]	Loss: 0.8007	LR: 0.100000
Training Epoch: 2 [2560/9756]	Loss: 0.7086	LR: 0.100000
Training Epoch: 2 [2816/9756]	Loss: 0.7027	LR: 0.100000
Training Epoch: 2 [3072/9756]	Loss: 0.7301	LR: 0.100000
Training Epoch: 2 [3328/9756]	Loss: 0.6816	LR: 0.100000
Training Epoch: 2 [3584/9756]	Loss: 0.8276	LR: 0.100000
Training Epoch: 2 [3840/9756]	Loss: 0.7043	LR: 0.100000
Training Epoch: 2 [4096/9756]	Loss: 0.7264	LR: 0.100000
Training Epoch: 2 [4352/9756]	Loss: 0.8016	LR: 0.100000
Training Epoch: 2 [4608/9756]	Loss: 0.7250	LR: 0.100000
Training Epoch: 2 [4864/9756]	Loss: 0.6793	LR: 0.100000
Training Epoch: 2 [5120/9756]	Loss: 0.6829	LR: 0.100000
Training Epoch: 2 [5376/9756]	Loss: 0.8201	LR: 0.100000
Training Epoch: 2 [5632/9756]	Loss: 0.6918	LR: 0.100000
Training Epoch: 2 [5888/9756]	Loss: 0.6838	LR: 0.100000
Training Epoch: 2 [6144/9756]	Loss: 0.6784	LR: 0.100000
Training Epoch: 2 [6400/9756]	Loss: 0.7444	LR: 0.100000
Training Epoch: 2 [6656/9756]	Loss: 0.7033	LR: 0.100000
Training Epoch: 2 [6912/9756]	Loss: 0.6836	LR: 0.100000
Training Epoch: 2 [7168/9756]	Loss: 0.6964	LR: 0.100000
Training Epoch: 2 [7424/9756]	Loss: 0.7188	LR: 0.100000
Training Epoch: 2 [7680/9756]	Loss: 0.6803	LR: 0.100000
Training Epoch: 2 [7936/9756]	Loss: 0.6917	LR: 0.100000
Training Epoch: 2 [8192/9756]	Loss: 0.6933	LR: 0.100000
Training Epoch: 2 [8448/9756]	Loss: 0.6860	LR: 0.100000
Training Epoch: 2 [8704/9756]	Loss: 0.6856	LR: 0.100000
Training Epoch: 2 [8960/9756]	Loss: 0.6806	LR: 0.100000
Training Epoch: 2 [9216/9756]	Loss: 0.6795	LR: 0.100000
Training Epoch: 2 [9472/9756]	Loss: 0.6812	LR: 0.100000
Training Epoch: 2 [9728/9756]	Loss: 0.6828	LR: 0.100000
Training Epoch: 2 [9756/9756]	Loss: 0.6937	LR: 0.100000
Epoch 2 - Average Train Loss: 0.7335, Train Accuracy: 0.5294
Epoch 2 training time consumed: 142.03s
Evaluating Network.....
Test set: Epoch: 2, Average loss: 0.0030, Accuracy: 0.5695, Time consumed:8.00s
Saving weights file to checkpoint/retrain/ResNet18/Saturday_26_July_2025_01h_54m_23s/ResNet18-MUCAC-seed4-ret25-2-best.pth
Training Epoch: 3 [256/9756]	Loss: 0.6748	LR: 0.100000
Training Epoch: 3 [512/9756]	Loss: 0.6735	LR: 0.100000
Training Epoch: 3 [768/9756]	Loss: 0.6818	LR: 0.100000
Training Epoch: 3 [1024/9756]	Loss: 0.6589	LR: 0.100000
Training Epoch: 3 [1280/9756]	Loss: 0.6637	LR: 0.100000
Training Epoch: 3 [1536/9756]	Loss: 0.7097	LR: 0.100000
Training Epoch: 3 [1792/9756]	Loss: 0.6779	LR: 0.100000
Training Epoch: 3 [2048/9756]	Loss: 0.6551	LR: 0.100000
Training Epoch: 3 [2304/9756]	Loss: 0.6783	LR: 0.100000
Training Epoch: 3 [2560/9756]	Loss: 0.6871	LR: 0.100000
Training Epoch: 3 [2816/9756]	Loss: 0.6817	LR: 0.100000
Training Epoch: 3 [3072/9756]	Loss: 0.7017	LR: 0.100000
Training Epoch: 3 [3328/9756]	Loss: 0.6823	LR: 0.100000
Training Epoch: 3 [3584/9756]	Loss: 0.6654	LR: 0.100000
Training Epoch: 3 [3840/9756]	Loss: 0.6822	LR: 0.100000
Training Epoch: 3 [4096/9756]	Loss: 0.6862	LR: 0.100000
Training Epoch: 3 [4352/9756]	Loss: 0.6718	LR: 0.100000
Training Epoch: 3 [4608/9756]	Loss: 0.6884	LR: 0.100000
Training Epoch: 3 [4864/9756]	Loss: 0.6431	LR: 0.100000
Training Epoch: 3 [5120/9756]	Loss: 0.6988	LR: 0.100000
Training Epoch: 3 [5376/9756]	Loss: 0.6798	LR: 0.100000
Training Epoch: 3 [5632/9756]	Loss: 0.6633	LR: 0.100000
Training Epoch: 3 [5888/9756]	Loss: 0.6830	LR: 0.100000
Training Epoch: 3 [6144/9756]	Loss: 0.6918	LR: 0.100000
Training Epoch: 3 [6400/9756]	Loss: 0.6801	LR: 0.100000
Training Epoch: 3 [6656/9756]	Loss: 0.6859	LR: 0.100000
Training Epoch: 3 [6912/9756]	Loss: 0.6711	LR: 0.100000
Training Epoch: 3 [7168/9756]	Loss: 0.6625	LR: 0.100000
Training Epoch: 3 [7424/9756]	Loss: 0.6834	LR: 0.100000
Training Epoch: 3 [7680/9756]	Loss: 0.6969	LR: 0.100000
Training Epoch: 3 [7936/9756]	Loss: 0.6803	LR: 0.100000
Training Epoch: 3 [8192/9756]	Loss: 0.6836	LR: 0.100000
Training Epoch: 3 [8448/9756]	Loss: 0.6595	LR: 0.100000
Training Epoch: 3 [8704/9756]	Loss: 0.6945	LR: 0.100000
Training Epoch: 3 [8960/9756]	Loss: 0.6886	LR: 0.100000
Training Epoch: 3 [9216/9756]	Loss: 0.6643	LR: 0.100000
Training Epoch: 3 [9472/9756]	Loss: 0.6717	LR: 0.100000
Training Epoch: 3 [9728/9756]	Loss: 0.6814	LR: 0.100000
Training Epoch: 3 [9756/9756]	Loss: 0.7285	LR: 0.100000
Epoch 3 - Average Train Loss: 0.6787, Train Accuracy: 0.5755
Epoch 3 training time consumed: 141.01s
Evaluating Network.....
Test set: Epoch: 3, Average loss: 0.0031, Accuracy: 0.5312, Time consumed:8.01s
Training Epoch: 4 [256/9756]	Loss: 0.6831	LR: 0.100000
Training Epoch: 4 [512/9756]	Loss: 0.6689	LR: 0.100000
Training Epoch: 4 [768/9756]	Loss: 0.6932	LR: 0.100000
Training Epoch: 4 [1024/9756]	Loss: 0.6799	LR: 0.100000
Training Epoch: 4 [1280/9756]	Loss: 0.7041	LR: 0.100000
Training Epoch: 4 [1536/9756]	Loss: 0.6906	LR: 0.100000
Training Epoch: 4 [1792/9756]	Loss: 0.6680	LR: 0.100000
Training Epoch: 4 [2048/9756]	Loss: 0.6666	LR: 0.100000
Training Epoch: 4 [2304/9756]	Loss: 0.6688	LR: 0.100000
Training Epoch: 4 [2560/9756]	Loss: 0.7063	LR: 0.100000
Training Epoch: 4 [2816/9756]	Loss: 0.6701	LR: 0.100000
Training Epoch: 4 [3072/9756]	Loss: 0.6872	LR: 0.100000
Training Epoch: 4 [3328/9756]	Loss: 0.6741	LR: 0.100000
Training Epoch: 4 [3584/9756]	Loss: 0.6803	LR: 0.100000
Training Epoch: 4 [3840/9756]	Loss: 0.6771	LR: 0.100000
Training Epoch: 4 [4096/9756]	Loss: 0.6745	LR: 0.100000
Training Epoch: 4 [4352/9756]	Loss: 0.6602	LR: 0.100000
Training Epoch: 4 [4608/9756]	Loss: 0.6773	LR: 0.100000
Training Epoch: 4 [4864/9756]	Loss: 0.6821	LR: 0.100000
Training Epoch: 4 [5120/9756]	Loss: 0.6831	LR: 0.100000
Training Epoch: 4 [5376/9756]	Loss: 0.6521	LR: 0.100000
Training Epoch: 4 [5632/9756]	Loss: 0.6728	LR: 0.100000
Training Epoch: 4 [5888/9756]	Loss: 0.6760	LR: 0.100000
Training Epoch: 4 [6144/9756]	Loss: 0.6692	LR: 0.100000
Training Epoch: 4 [6400/9756]	Loss: 0.6765	LR: 0.100000
Training Epoch: 4 [6656/9756]	Loss: 0.6689	LR: 0.100000
Training Epoch: 4 [6912/9756]	Loss: 0.6413	LR: 0.100000
Training Epoch: 4 [7168/9756]	Loss: 0.6597	LR: 0.100000
Training Epoch: 4 [7424/9756]	Loss: 0.6774	LR: 0.100000
Training Epoch: 4 [7680/9756]	Loss: 0.6884	LR: 0.100000
Training Epoch: 4 [7936/9756]	Loss: 0.6946	LR: 0.100000
Training Epoch: 4 [8192/9756]	Loss: 0.6417	LR: 0.100000
Training Epoch: 4 [8448/9756]	Loss: 0.6989	LR: 0.100000
Training Epoch: 4 [8704/9756]	Loss: 0.6701	LR: 0.100000
Training Epoch: 4 [8960/9756]	Loss: 0.6655	LR: 0.100000
Training Epoch: 4 [9216/9756]	Loss: 0.6548	LR: 0.100000
Training Epoch: 4 [9472/9756]	Loss: 0.6584	LR: 0.100000
Training Epoch: 4 [9728/9756]	Loss: 0.6732	LR: 0.100000
Training Epoch: 4 [9756/9756]	Loss: 0.6856	LR: 0.100000
Epoch 4 - Average Train Loss: 0.6746, Train Accuracy: 0.5861
Epoch 4 training time consumed: 140.59s
Evaluating Network.....
Test set: Epoch: 4, Average loss: 0.0031, Accuracy: 0.5298, Time consumed:7.91s
Training Epoch: 5 [256/9756]	Loss: 0.6583	LR: 0.100000
Training Epoch: 5 [512/9756]	Loss: 0.6546	LR: 0.100000
Training Epoch: 5 [768/9756]	Loss: 0.6932	LR: 0.100000
Training Epoch: 5 [1024/9756]	Loss: 0.6638	LR: 0.100000
Training Epoch: 5 [1280/9756]	Loss: 0.6638	LR: 0.100000
Training Epoch: 5 [1536/9756]	Loss: 0.6428	LR: 0.100000
Training Epoch: 5 [1792/9756]	Loss: 0.6505	LR: 0.100000
Training Epoch: 5 [2048/9756]	Loss: 0.6716	LR: 0.100000
Training Epoch: 5 [2304/9756]	Loss: 0.6810	LR: 0.100000
Training Epoch: 5 [2560/9756]	Loss: 0.6883	LR: 0.100000
Training Epoch: 5 [2816/9756]	Loss: 0.6528	LR: 0.100000
Training Epoch: 5 [3072/9756]	Loss: 0.6342	LR: 0.100000
Training Epoch: 5 [3328/9756]	Loss: 0.6819	LR: 0.100000
Training Epoch: 5 [3584/9756]	Loss: 0.6582	LR: 0.100000
Training Epoch: 5 [3840/9756]	Loss: 0.6962	LR: 0.100000
Training Epoch: 5 [4096/9756]	Loss: 0.6706	LR: 0.100000
Training Epoch: 5 [4352/9756]	Loss: 0.6465	LR: 0.100000
Training Epoch: 5 [4608/9756]	Loss: 0.6477	LR: 0.100000
Training Epoch: 5 [4864/9756]	Loss: 0.6558	LR: 0.100000
Training Epoch: 5 [5120/9756]	Loss: 0.6778	LR: 0.100000
Training Epoch: 5 [5376/9756]	Loss: 0.6477	LR: 0.100000
Training Epoch: 5 [5632/9756]	Loss: 0.6455	LR: 0.100000
Training Epoch: 5 [5888/9756]	Loss: 0.6395	LR: 0.100000
Training Epoch: 5 [6144/9756]	Loss: 0.6501	LR: 0.100000
Training Epoch: 5 [6400/9756]	Loss: 0.6321	LR: 0.100000
Training Epoch: 5 [6656/9756]	Loss: 0.6941	LR: 0.100000
Training Epoch: 5 [6912/9756]	Loss: 0.6191	LR: 0.100000
Training Epoch: 5 [7168/9756]	Loss: 0.6440	LR: 0.100000
Training Epoch: 5 [7424/9756]	Loss: 0.6367	LR: 0.100000
Training Epoch: 5 [7680/9756]	Loss: 0.6444	LR: 0.100000
Training Epoch: 5 [7936/9756]	Loss: 0.6389	LR: 0.100000
Training Epoch: 5 [8192/9756]	Loss: 0.6071	LR: 0.100000
Training Epoch: 5 [8448/9756]	Loss: 0.6539	LR: 0.100000
Training Epoch: 5 [8704/9756]	Loss: 0.6627	LR: 0.100000
Training Epoch: 5 [8960/9756]	Loss: 0.5926	LR: 0.100000
Training Epoch: 5 [9216/9756]	Loss: 0.6498	LR: 0.100000
Training Epoch: 5 [9472/9756]	Loss: 0.6061	LR: 0.100000
Training Epoch: 5 [9728/9756]	Loss: 0.6057	LR: 0.100000
Training Epoch: 5 [9756/9756]	Loss: 0.6597	LR: 0.100000
Epoch 5 - Average Train Loss: 0.6516, Train Accuracy: 0.6195
Epoch 5 training time consumed: 140.71s
Evaluating Network.....
Test set: Epoch: 5, Average loss: 0.0029, Accuracy: 0.6339, Time consumed:7.85s
Saving weights file to checkpoint/retrain/ResNet18/Saturday_26_July_2025_01h_54m_23s/ResNet18-MUCAC-seed4-ret25-5-best.pth
Training Epoch: 6 [256/9756]	Loss: 0.6560	LR: 0.100000
Training Epoch: 6 [512/9756]	Loss: 0.6830	LR: 0.100000
Training Epoch: 6 [768/9756]	Loss: 0.7014	LR: 0.100000
Training Epoch: 6 [1024/9756]	Loss: 0.6986	LR: 0.100000
Training Epoch: 6 [1280/9756]	Loss: 0.6588	LR: 0.100000
Training Epoch: 6 [1536/9756]	Loss: 0.6776	LR: 0.100000
Training Epoch: 6 [1792/9756]	Loss: 0.6857	LR: 0.100000
Training Epoch: 6 [2048/9756]	Loss: 0.6639	LR: 0.100000
Training Epoch: 6 [2304/9756]	Loss: 0.6242	LR: 0.100000
Training Epoch: 6 [2560/9756]	Loss: 0.6243	LR: 0.100000
Training Epoch: 6 [2816/9756]	Loss: 0.6398	LR: 0.100000
Training Epoch: 6 [3072/9756]	Loss: 0.6515	LR: 0.100000
Training Epoch: 6 [3328/9756]	Loss: 0.6041	LR: 0.100000
Training Epoch: 6 [3584/9756]	Loss: 0.6174	LR: 0.100000
Training Epoch: 6 [3840/9756]	Loss: 0.5895	LR: 0.100000
Training Epoch: 6 [4096/9756]	Loss: 0.5822	LR: 0.100000
Training Epoch: 6 [4352/9756]	Loss: 0.5990	LR: 0.100000
Training Epoch: 6 [4608/9756]	Loss: 0.6194	LR: 0.100000
Training Epoch: 6 [4864/9756]	Loss: 0.6071	LR: 0.100000
Training Epoch: 6 [5120/9756]	Loss: 0.6020	LR: 0.100000
Training Epoch: 6 [5376/9756]	Loss: 0.5615	LR: 0.100000
Training Epoch: 6 [5632/9756]	Loss: 0.6290	LR: 0.100000
Training Epoch: 6 [5888/9756]	Loss: 0.6109	LR: 0.100000
Training Epoch: 6 [6144/9756]	Loss: 0.5941	LR: 0.100000
Training Epoch: 6 [6400/9756]	Loss: 0.6275	LR: 0.100000
Training Epoch: 6 [6656/9756]	Loss: 0.6200	LR: 0.100000
Training Epoch: 6 [6912/9756]	Loss: 0.5802	LR: 0.100000
Training Epoch: 6 [7168/9756]	Loss: 0.5961	LR: 0.100000
Training Epoch: 6 [7424/9756]	Loss: 0.5897	LR: 0.100000
Training Epoch: 6 [7680/9756]	Loss: 0.5857	LR: 0.100000
Training Epoch: 6 [7936/9756]	Loss: 0.6021	LR: 0.100000
Training Epoch: 6 [8192/9756]	Loss: 0.5947	LR: 0.100000
Training Epoch: 6 [8448/9756]	Loss: 0.6151	LR: 0.100000
Training Epoch: 6 [8704/9756]	Loss: 0.5833	LR: 0.100000
Training Epoch: 6 [8960/9756]	Loss: 0.5385	LR: 0.100000
Training Epoch: 6 [9216/9756]	Loss: 0.5671	LR: 0.100000
Training Epoch: 6 [9472/9756]	Loss: 0.5857	LR: 0.100000
Training Epoch: 6 [9728/9756]	Loss: 0.5910	LR: 0.100000
Training Epoch: 6 [9756/9756]	Loss: 0.6639	LR: 0.100000
Epoch 6 - Average Train Loss: 0.6174, Train Accuracy: 0.6587
Epoch 6 training time consumed: 141.00s
Evaluating Network.....
Test set: Epoch: 6, Average loss: 0.0026, Accuracy: 0.7065, Time consumed:8.07s
Saving weights file to checkpoint/retrain/ResNet18/Saturday_26_July_2025_01h_54m_23s/ResNet18-MUCAC-seed4-ret25-6-best.pth
Training Epoch: 7 [256/9756]	Loss: 0.5852	LR: 0.100000
Training Epoch: 7 [512/9756]	Loss: 0.5647	LR: 0.100000
Training Epoch: 7 [768/9756]	Loss: 0.5379	LR: 0.100000
Training Epoch: 7 [1024/9756]	Loss: 0.5522	LR: 0.100000
Training Epoch: 7 [1280/9756]	Loss: 0.5790	LR: 0.100000
Training Epoch: 7 [1536/9756]	Loss: 0.6011	LR: 0.100000
Training Epoch: 7 [1792/9756]	Loss: 0.5450	LR: 0.100000
Training Epoch: 7 [2048/9756]	Loss: 0.6000	LR: 0.100000
Training Epoch: 7 [2304/9756]	Loss: 0.5949	LR: 0.100000
Training Epoch: 7 [2560/9756]	Loss: 0.5488	LR: 0.100000
Training Epoch: 7 [2816/9756]	Loss: 0.6108	LR: 0.100000
Training Epoch: 7 [3072/9756]	Loss: 0.5835	LR: 0.100000
Training Epoch: 7 [3328/9756]	Loss: 0.5556	LR: 0.100000
Training Epoch: 7 [3584/9756]	Loss: 0.5546	LR: 0.100000
Training Epoch: 7 [3840/9756]	Loss: 0.5795	LR: 0.100000
Training Epoch: 7 [4096/9756]	Loss: 0.5850	LR: 0.100000
Training Epoch: 7 [4352/9756]	Loss: 0.5737	LR: 0.100000
Training Epoch: 7 [4608/9756]	Loss: 0.5153	LR: 0.100000
Training Epoch: 7 [4864/9756]	Loss: 0.5034	LR: 0.100000
Training Epoch: 7 [5120/9756]	Loss: 0.5269	LR: 0.100000
Training Epoch: 7 [5376/9756]	Loss: 0.5163	LR: 0.100000
Training Epoch: 7 [5632/9756]	Loss: 0.5177	LR: 0.100000
Training Epoch: 7 [5888/9756]	Loss: 0.5719	LR: 0.100000
Training Epoch: 7 [6144/9756]	Loss: 0.5182	LR: 0.100000
Training Epoch: 7 [6400/9756]	Loss: 0.4795	LR: 0.100000
Training Epoch: 7 [6656/9756]	Loss: 0.5057	LR: 0.100000
Training Epoch: 7 [6912/9756]	Loss: 0.5535	LR: 0.100000
Training Epoch: 7 [7168/9756]	Loss: 0.5561	LR: 0.100000
Training Epoch: 7 [7424/9756]	Loss: 0.5000	LR: 0.100000
Training Epoch: 7 [7680/9756]	Loss: 0.4807	LR: 0.100000
Training Epoch: 7 [7936/9756]	Loss: 0.4793	LR: 0.100000
Training Epoch: 7 [8192/9756]	Loss: 0.4674	LR: 0.100000
Training Epoch: 7 [8448/9756]	Loss: 0.4791	LR: 0.100000
Training Epoch: 7 [8704/9756]	Loss: 0.4709	LR: 0.100000
Training Epoch: 7 [8960/9756]	Loss: 0.5120	LR: 0.100000
Training Epoch: 7 [9216/9756]	Loss: 0.4443	LR: 0.100000
Training Epoch: 7 [9472/9756]	Loss: 0.4767	LR: 0.100000
Training Epoch: 7 [9728/9756]	Loss: 0.4713	LR: 0.100000
Training Epoch: 7 [9756/9756]	Loss: 0.3968	LR: 0.100000
Epoch 7 - Average Train Loss: 0.5338, Train Accuracy: 0.7387
Epoch 7 training time consumed: 140.47s
Evaluating Network.....
Test set: Epoch: 7, Average loss: 0.0021, Accuracy: 0.7864, Time consumed:8.08s
Saving weights file to checkpoint/retrain/ResNet18/Saturday_26_July_2025_01h_54m_23s/ResNet18-MUCAC-seed4-ret25-7-best.pth
Training Epoch: 8 [256/9756]	Loss: 0.5240	LR: 0.100000
Training Epoch: 8 [512/9756]	Loss: 0.4722	LR: 0.100000
Training Epoch: 8 [768/9756]	Loss: 0.5761	LR: 0.100000
Training Epoch: 8 [1024/9756]	Loss: 0.5368	LR: 0.100000
Training Epoch: 8 [1280/9756]	Loss: 0.4295	LR: 0.100000
Training Epoch: 8 [1536/9756]	Loss: 0.5008	LR: 0.100000
Training Epoch: 8 [1792/9756]	Loss: 0.5464	LR: 0.100000
Training Epoch: 8 [2048/9756]	Loss: 0.5438	LR: 0.100000
Training Epoch: 8 [2304/9756]	Loss: 0.4762	LR: 0.100000
Training Epoch: 8 [2560/9756]	Loss: 0.4938	LR: 0.100000
Training Epoch: 8 [2816/9756]	Loss: 0.4990	LR: 0.100000
Training Epoch: 8 [3072/9756]	Loss: 0.4417	LR: 0.100000
Training Epoch: 8 [3328/9756]	Loss: 0.4840	LR: 0.100000
Training Epoch: 8 [3584/9756]	Loss: 0.4598	LR: 0.100000
Training Epoch: 8 [3840/9756]	Loss: 0.4697	LR: 0.100000
Training Epoch: 8 [4096/9756]	Loss: 0.4672	LR: 0.100000
Training Epoch: 8 [4352/9756]	Loss: 0.4314	LR: 0.100000
Training Epoch: 8 [4608/9756]	Loss: 0.4150	LR: 0.100000
Training Epoch: 8 [4864/9756]	Loss: 0.5140	LR: 0.100000
Training Epoch: 8 [5120/9756]	Loss: 0.4350	LR: 0.100000
Training Epoch: 8 [5376/9756]	Loss: 0.4676	LR: 0.100000
Training Epoch: 8 [5632/9756]	Loss: 0.4484	LR: 0.100000
Training Epoch: 8 [5888/9756]	Loss: 0.5498	LR: 0.100000
Training Epoch: 8 [6144/9756]	Loss: 0.4760	LR: 0.100000
Training Epoch: 8 [6400/9756]	Loss: 0.4087	LR: 0.100000
Training Epoch: 8 [6656/9756]	Loss: 0.4543	LR: 0.100000
Training Epoch: 8 [6912/9756]	Loss: 0.3680	LR: 0.100000
Training Epoch: 8 [7168/9756]	Loss: 0.4684	LR: 0.100000
Training Epoch: 8 [7424/9756]	Loss: 0.4548	LR: 0.100000
Training Epoch: 8 [7680/9756]	Loss: 0.4863	LR: 0.100000
Training Epoch: 8 [7936/9756]	Loss: 0.4405	LR: 0.100000
Training Epoch: 8 [8192/9756]	Loss: 0.4330	LR: 0.100000
Training Epoch: 8 [8448/9756]	Loss: 0.4719	LR: 0.100000
Training Epoch: 8 [8704/9756]	Loss: 0.5389	LR: 0.100000
Training Epoch: 8 [8960/9756]	Loss: 0.5032	LR: 0.100000
Training Epoch: 8 [9216/9756]	Loss: 0.4341	LR: 0.100000
Training Epoch: 8 [9472/9756]	Loss: 0.4686	LR: 0.100000
Training Epoch: 8 [9728/9756]	Loss: 0.4595	LR: 0.100000
Training Epoch: 8 [9756/9756]	Loss: 0.4908	LR: 0.100000
Epoch 8 - Average Train Loss: 0.4750, Train Accuracy: 0.7783
Epoch 8 training time consumed: 140.73s
Evaluating Network.....
Test set: Epoch: 8, Average loss: 0.0021, Accuracy: 0.7869, Time consumed:7.77s
Saving weights file to checkpoint/retrain/ResNet18/Saturday_26_July_2025_01h_54m_23s/ResNet18-MUCAC-seed4-ret25-8-best.pth
Training Epoch: 9 [256/9756]	Loss: 0.4132	LR: 0.100000
Training Epoch: 9 [512/9756]	Loss: 0.4341	LR: 0.100000
Training Epoch: 9 [768/9756]	Loss: 0.5317	LR: 0.100000
Training Epoch: 9 [1024/9756]	Loss: 0.4467	LR: 0.100000
Training Epoch: 9 [1280/9756]	Loss: 0.4201	LR: 0.100000
Training Epoch: 9 [1536/9756]	Loss: 0.5071	LR: 0.100000
Training Epoch: 9 [1792/9756]	Loss: 0.4431	LR: 0.100000
Training Epoch: 9 [2048/9756]	Loss: 0.4513	LR: 0.100000
Training Epoch: 9 [2304/9756]	Loss: 0.4432	LR: 0.100000
Training Epoch: 9 [2560/9756]	Loss: 0.3854	LR: 0.100000
Training Epoch: 9 [2816/9756]	Loss: 0.4322	LR: 0.100000
Training Epoch: 9 [3072/9756]	Loss: 0.3894	LR: 0.100000
Training Epoch: 9 [3328/9756]	Loss: 0.4457	LR: 0.100000
Training Epoch: 9 [3584/9756]	Loss: 0.3909	LR: 0.100000
Training Epoch: 9 [3840/9756]	Loss: 0.4867	LR: 0.100000
Training Epoch: 9 [4096/9756]	Loss: 0.4604	LR: 0.100000
Training Epoch: 9 [4352/9756]	Loss: 0.4471	LR: 0.100000
Training Epoch: 9 [4608/9756]	Loss: 0.4360	LR: 0.100000
Training Epoch: 9 [4864/9756]	Loss: 0.3990	LR: 0.100000
Training Epoch: 9 [5120/9756]	Loss: 0.3688	LR: 0.100000
Training Epoch: 9 [5376/9756]	Loss: 0.4104	LR: 0.100000
Training Epoch: 9 [5632/9756]	Loss: 0.3863	LR: 0.100000
Training Epoch: 9 [5888/9756]	Loss: 0.4219	LR: 0.100000
Training Epoch: 9 [6144/9756]	Loss: 0.4125	LR: 0.100000
Training Epoch: 9 [6400/9756]	Loss: 0.3157	LR: 0.100000
Training Epoch: 9 [6656/9756]	Loss: 0.3615	LR: 0.100000
Training Epoch: 9 [6912/9756]	Loss: 0.4115	LR: 0.100000
Training Epoch: 9 [7168/9756]	Loss: 0.3531	LR: 0.100000
Training Epoch: 9 [7424/9756]	Loss: 0.4138	LR: 0.100000
Training Epoch: 9 [7680/9756]	Loss: 0.4142	LR: 0.100000
Training Epoch: 9 [7936/9756]	Loss: 0.3698	LR: 0.100000
Training Epoch: 9 [8192/9756]	Loss: 0.3231	LR: 0.100000
Training Epoch: 9 [8448/9756]	Loss: 0.3697	LR: 0.100000
Training Epoch: 9 [8704/9756]	Loss: 0.4092	LR: 0.100000
Training Epoch: 9 [8960/9756]	Loss: 0.3909	LR: 0.100000
Training Epoch: 9 [9216/9756]	Loss: 0.3777	LR: 0.100000
Training Epoch: 9 [9472/9756]	Loss: 0.4132	LR: 0.100000
Training Epoch: 9 [9728/9756]	Loss: 0.3670	LR: 0.100000
Training Epoch: 9 [9756/9756]	Loss: 0.3404	LR: 0.100000
Epoch 9 - Average Train Loss: 0.4117, Train Accuracy: 0.8145
Epoch 9 training time consumed: 140.84s
Evaluating Network.....
Test set: Epoch: 9, Average loss: 0.0044, Accuracy: 0.5564, Time consumed:7.89s
Training Epoch: 10 [256/9756]	Loss: 0.5796	LR: 0.020000
Training Epoch: 10 [512/9756]	Loss: 0.4300	LR: 0.020000
Training Epoch: 10 [768/9756]	Loss: 0.4477	LR: 0.020000
Training Epoch: 10 [1024/9756]	Loss: 0.3448	LR: 0.020000
Training Epoch: 10 [1280/9756]	Loss: 0.3502	LR: 0.020000
Training Epoch: 10 [1536/9756]	Loss: 0.3932	LR: 0.020000
Training Epoch: 10 [1792/9756]	Loss: 0.3646	LR: 0.020000
Training Epoch: 10 [2048/9756]	Loss: 0.3535	LR: 0.020000
Training Epoch: 10 [2304/9756]	Loss: 0.4125	LR: 0.020000
Training Epoch: 10 [2560/9756]	Loss: 0.3805	LR: 0.020000
Training Epoch: 10 [2816/9756]	Loss: 0.4468	LR: 0.020000
Training Epoch: 10 [3072/9756]	Loss: 0.3849	LR: 0.020000
Training Epoch: 10 [3328/9756]	Loss: 0.3396	LR: 0.020000
Training Epoch: 10 [3584/9756]	Loss: 0.3222	LR: 0.020000
Training Epoch: 10 [3840/9756]	Loss: 0.3583	LR: 0.020000
Training Epoch: 10 [4096/9756]	Loss: 0.3309	LR: 0.020000
Training Epoch: 10 [4352/9756]	Loss: 0.3377	LR: 0.020000
Training Epoch: 10 [4608/9756]	Loss: 0.3280	LR: 0.020000
Training Epoch: 10 [4864/9756]	Loss: 0.2797	LR: 0.020000
Training Epoch: 10 [5120/9756]	Loss: 0.3735	LR: 0.020000
Training Epoch: 10 [5376/9756]	Loss: 0.3796	LR: 0.020000
Training Epoch: 10 [5632/9756]	Loss: 0.3425	LR: 0.020000
Training Epoch: 10 [5888/9756]	Loss: 0.2767	LR: 0.020000
Training Epoch: 10 [6144/9756]	Loss: 0.3206	LR: 0.020000
Training Epoch: 10 [6400/9756]	Loss: 0.3599	LR: 0.020000
Training Epoch: 10 [6656/9756]	Loss: 0.3431	LR: 0.020000
Training Epoch: 10 [6912/9756]	Loss: 0.2904	LR: 0.020000
Training Epoch: 10 [7168/9756]	Loss: 0.3411	LR: 0.020000
Training Epoch: 10 [7424/9756]	Loss: 0.3295	LR: 0.020000
Training Epoch: 10 [7680/9756]	Loss: 0.3085	LR: 0.020000
Training Epoch: 10 [7936/9756]	Loss: 0.3026	LR: 0.020000
Training Epoch: 10 [8192/9756]	Loss: 0.2852	LR: 0.020000
Training Epoch: 10 [8448/9756]	Loss: 0.3312	LR: 0.020000
Training Epoch: 10 [8704/9756]	Loss: 0.3395	LR: 0.020000
Training Epoch: 10 [8960/9756]	Loss: 0.3643	LR: 0.020000
Training Epoch: 10 [9216/9756]	Loss: 0.2870	LR: 0.020000
Training Epoch: 10 [9472/9756]	Loss: 0.3148	LR: 0.020000
Training Epoch: 10 [9728/9756]	Loss: 0.3166	LR: 0.020000
Training Epoch: 10 [9756/9756]	Loss: 0.3274	LR: 0.020000
Epoch 10 - Average Train Loss: 0.3523, Train Accuracy: 0.8434
Epoch 10 training time consumed: 140.57s
Evaluating Network.....
Test set: Epoch: 10, Average loss: 0.0015, Accuracy: 0.8673, Time consumed:7.94s
Saving weights file to checkpoint/retrain/ResNet18/Saturday_26_July_2025_01h_54m_23s/ResNet18-MUCAC-seed4-ret25-10-best.pth
Training Epoch: 11 [256/9756]	Loss: 0.2695	LR: 0.020000
Training Epoch: 11 [512/9756]	Loss: 0.2708	LR: 0.020000
Training Epoch: 11 [768/9756]	Loss: 0.3071	LR: 0.020000
Training Epoch: 11 [1024/9756]	Loss: 0.3273	LR: 0.020000
Training Epoch: 11 [1280/9756]	Loss: 0.2492	LR: 0.020000
Training Epoch: 11 [1536/9756]	Loss: 0.3189	LR: 0.020000
Training Epoch: 11 [1792/9756]	Loss: 0.2168	LR: 0.020000
Training Epoch: 11 [2048/9756]	Loss: 0.3424	LR: 0.020000
Training Epoch: 11 [2304/9756]	Loss: 0.2967	LR: 0.020000
Training Epoch: 11 [2560/9756]	Loss: 0.3133	LR: 0.020000
Training Epoch: 11 [2816/9756]	Loss: 0.3500	LR: 0.020000
Training Epoch: 11 [3072/9756]	Loss: 0.3708	LR: 0.020000
Training Epoch: 11 [3328/9756]	Loss: 0.2818	LR: 0.020000
Training Epoch: 11 [3584/9756]	Loss: 0.2748	LR: 0.020000
Training Epoch: 11 [3840/9756]	Loss: 0.2694	LR: 0.020000
Training Epoch: 11 [4096/9756]	Loss: 0.3595	LR: 0.020000
Training Epoch: 11 [4352/9756]	Loss: 0.2379	LR: 0.020000
Training Epoch: 11 [4608/9756]	Loss: 0.3209	LR: 0.020000
Training Epoch: 11 [4864/9756]	Loss: 0.2975	LR: 0.020000
Training Epoch: 11 [5120/9756]	Loss: 0.3034	LR: 0.020000
Training Epoch: 11 [5376/9756]	Loss: 0.3301	LR: 0.020000
Training Epoch: 11 [5632/9756]	Loss: 0.3177	LR: 0.020000
Training Epoch: 11 [5888/9756]	Loss: 0.2721	LR: 0.020000
Training Epoch: 11 [6144/9756]	Loss: 0.2460	LR: 0.020000
Training Epoch: 11 [6400/9756]	Loss: 0.2449	LR: 0.020000
Training Epoch: 11 [6656/9756]	Loss: 0.3110	LR: 0.020000
Training Epoch: 11 [6912/9756]	Loss: 0.2610	LR: 0.020000
Training Epoch: 11 [7168/9756]	Loss: 0.2463	LR: 0.020000
Training Epoch: 11 [7424/9756]	Loss: 0.3131	LR: 0.020000
Training Epoch: 11 [7680/9756]	Loss: 0.3219	LR: 0.020000
Training Epoch: 11 [7936/9756]	Loss: 0.3134	LR: 0.020000
Training Epoch: 11 [8192/9756]	Loss: 0.2851	LR: 0.020000
Training Epoch: 11 [8448/9756]	Loss: 0.3250	LR: 0.020000
Training Epoch: 11 [8704/9756]	Loss: 0.2695	LR: 0.020000
Training Epoch: 11 [8960/9756]	Loss: 0.3116	LR: 0.020000
Training Epoch: 11 [9216/9756]	Loss: 0.3081	LR: 0.020000
Training Epoch: 11 [9472/9756]	Loss: 0.3227	LR: 0.020000
Training Epoch: 11 [9728/9756]	Loss: 0.2958	LR: 0.020000
Training Epoch: 11 [9756/9756]	Loss: 0.2733	LR: 0.020000
Epoch 11 - Average Train Loss: 0.2966, Train Accuracy: 0.8745
Epoch 11 training time consumed: 140.54s
Evaluating Network.....
Test set: Epoch: 11, Average loss: 0.0011, Accuracy: 0.8949, Time consumed:8.16s
Saving weights file to checkpoint/retrain/ResNet18/Saturday_26_July_2025_01h_54m_23s/ResNet18-MUCAC-seed4-ret25-11-best.pth
Training Epoch: 12 [256/9756]	Loss: 0.2758	LR: 0.020000
Training Epoch: 12 [512/9756]	Loss: 0.2259	LR: 0.020000
Training Epoch: 12 [768/9756]	Loss: 0.3193	LR: 0.020000
Training Epoch: 12 [1024/9756]	Loss: 0.3105	LR: 0.020000
Training Epoch: 12 [1280/9756]	Loss: 0.2776	LR: 0.020000
Training Epoch: 12 [1536/9756]	Loss: 0.2533	LR: 0.020000
Training Epoch: 12 [1792/9756]	Loss: 0.3640	LR: 0.020000
Training Epoch: 12 [2048/9756]	Loss: 0.2477	LR: 0.020000
Training Epoch: 12 [2304/9756]	Loss: 0.2780	LR: 0.020000
Training Epoch: 12 [2560/9756]	Loss: 0.2778	LR: 0.020000
Training Epoch: 12 [2816/9756]	Loss: 0.2123	LR: 0.020000
Training Epoch: 12 [3072/9756]	Loss: 0.2618	LR: 0.020000
Training Epoch: 12 [3328/9756]	Loss: 0.3569	LR: 0.020000
Training Epoch: 12 [3584/9756]	Loss: 0.2395	LR: 0.020000
Training Epoch: 12 [3840/9756]	Loss: 0.2984	LR: 0.020000
Training Epoch: 12 [4096/9756]	Loss: 0.2624	LR: 0.020000
Training Epoch: 12 [4352/9756]	Loss: 0.2741	LR: 0.020000
Training Epoch: 12 [4608/9756]	Loss: 0.3337	LR: 0.020000
Training Epoch: 12 [4864/9756]	Loss: 0.2084	LR: 0.020000
Training Epoch: 12 [5120/9756]	Loss: 0.2984	LR: 0.020000
Training Epoch: 12 [5376/9756]	Loss: 0.2836	LR: 0.020000
Training Epoch: 12 [5632/9756]	Loss: 0.2616	LR: 0.020000
Training Epoch: 12 [5888/9756]	Loss: 0.2561	LR: 0.020000
Training Epoch: 12 [6144/9756]	Loss: 0.2729	LR: 0.020000
Training Epoch: 12 [6400/9756]	Loss: 0.2642	LR: 0.020000
Training Epoch: 12 [6656/9756]	Loss: 0.2721	LR: 0.020000
Training Epoch: 12 [6912/9756]	Loss: 0.3250	LR: 0.020000
Training Epoch: 12 [7168/9756]	Loss: 0.3125	LR: 0.020000
Training Epoch: 12 [7424/9756]	Loss: 0.2856	LR: 0.020000
Training Epoch: 12 [7680/9756]	Loss: 0.2938	LR: 0.020000
Training Epoch: 12 [7936/9756]	Loss: 0.3487	LR: 0.020000
Training Epoch: 12 [8192/9756]	Loss: 0.2220	LR: 0.020000
Training Epoch: 12 [8448/9756]	Loss: 0.3383	LR: 0.020000
Training Epoch: 12 [8704/9756]	Loss: 0.2699	LR: 0.020000
Training Epoch: 12 [8960/9756]	Loss: 0.2896	LR: 0.020000
Training Epoch: 12 [9216/9756]	Loss: 0.2579	LR: 0.020000
Training Epoch: 12 [9472/9756]	Loss: 0.2450	LR: 0.020000
Training Epoch: 12 [9728/9756]	Loss: 0.2489	LR: 0.020000
Training Epoch: 12 [9756/9756]	Loss: 0.5350	LR: 0.020000
Epoch 12 - Average Train Loss: 0.2803, Train Accuracy: 0.8835
Epoch 12 training time consumed: 140.07s
Evaluating Network.....
Test set: Epoch: 12, Average loss: 0.0014, Accuracy: 0.8760, Time consumed:8.09s
Training Epoch: 13 [256/9756]	Loss: 0.3318	LR: 0.020000
Training Epoch: 13 [512/9756]	Loss: 0.3656	LR: 0.020000
Training Epoch: 13 [768/9756]	Loss: 0.2545	LR: 0.020000
Training Epoch: 13 [1024/9756]	Loss: 0.3262	LR: 0.020000
Training Epoch: 13 [1280/9756]	Loss: 0.4071	LR: 0.020000
Training Epoch: 13 [1536/9756]	Loss: 0.3901	LR: 0.020000
Training Epoch: 13 [1792/9756]	Loss: 0.2886	LR: 0.020000
Training Epoch: 13 [2048/9756]	Loss: 0.3096	LR: 0.020000
Training Epoch: 13 [2304/9756]	Loss: 0.2994	LR: 0.020000
Training Epoch: 13 [2560/9756]	Loss: 0.3478	LR: 0.020000
Training Epoch: 13 [2816/9756]	Loss: 0.3238	LR: 0.020000
Training Epoch: 13 [3072/9756]	Loss: 0.3225	LR: 0.020000
Training Epoch: 13 [3328/9756]	Loss: 0.2553	LR: 0.020000
Training Epoch: 13 [3584/9756]	Loss: 0.2817	LR: 0.020000
Training Epoch: 13 [3840/9756]	Loss: 0.3028	LR: 0.020000
Training Epoch: 13 [4096/9756]	Loss: 0.2610	LR: 0.020000
Training Epoch: 13 [4352/9756]	Loss: 0.2603	LR: 0.020000
Training Epoch: 13 [4608/9756]	Loss: 0.2783	LR: 0.020000
Training Epoch: 13 [4864/9756]	Loss: 0.3155	LR: 0.020000
Training Epoch: 13 [5120/9756]	Loss: 0.2928	LR: 0.020000
Training Epoch: 13 [5376/9756]	Loss: 0.3355	LR: 0.020000
Training Epoch: 13 [5632/9756]	Loss: 0.2813	LR: 0.020000
Training Epoch: 13 [5888/9756]	Loss: 0.2592	LR: 0.020000
Training Epoch: 13 [6144/9756]	Loss: 0.2287	LR: 0.020000
Training Epoch: 13 [6400/9756]	Loss: 0.2498	LR: 0.020000
Training Epoch: 13 [6656/9756]	Loss: 0.2676	LR: 0.020000
Training Epoch: 13 [6912/9756]	Loss: 0.3292	LR: 0.020000
Training Epoch: 13 [7168/9756]	Loss: 0.2862	LR: 0.020000
Training Epoch: 13 [7424/9756]	Loss: 0.2339	LR: 0.020000
Training Epoch: 13 [7680/9756]	Loss: 0.2523	LR: 0.020000
Training Epoch: 13 [7936/9756]	Loss: 0.2092	LR: 0.020000
Training Epoch: 13 [8192/9756]	Loss: 0.2739	LR: 0.020000
Training Epoch: 13 [8448/9756]	Loss: 0.2496	LR: 0.020000
Training Epoch: 13 [8704/9756]	Loss: 0.2437	LR: 0.020000
Training Epoch: 13 [8960/9756]	Loss: 0.3172	LR: 0.020000
Training Epoch: 13 [9216/9756]	Loss: 0.2466	LR: 0.020000
Training Epoch: 13 [9472/9756]	Loss: 0.2598	LR: 0.020000
Training Epoch: 13 [9728/9756]	Loss: 0.2072	LR: 0.020000
Training Epoch: 13 [9756/9756]	Loss: 0.3843	LR: 0.020000
Epoch 13 - Average Train Loss: 0.2883, Train Accuracy: 0.8789
Epoch 13 training time consumed: 140.07s
Evaluating Network.....
Test set: Epoch: 13, Average loss: 0.0012, Accuracy: 0.8814, Time consumed:8.05s
Training Epoch: 14 [256/9756]	Loss: 0.2648	LR: 0.020000
Training Epoch: 14 [512/9756]	Loss: 0.3208	LR: 0.020000
Training Epoch: 14 [768/9756]	Loss: 0.2743	LR: 0.020000
Training Epoch: 14 [1024/9756]	Loss: 0.2477	LR: 0.020000
Training Epoch: 14 [1280/9756]	Loss: 0.2953	LR: 0.020000
Training Epoch: 14 [1536/9756]	Loss: 0.2666	LR: 0.020000
Training Epoch: 14 [1792/9756]	Loss: 0.1940	LR: 0.020000
Training Epoch: 14 [2048/9756]	Loss: 0.2695	LR: 0.020000
Training Epoch: 14 [2304/9756]	Loss: 0.2293	LR: 0.020000
Training Epoch: 14 [2560/9756]	Loss: 0.2617	LR: 0.020000
Training Epoch: 14 [2816/9756]	Loss: 0.2334	LR: 0.020000
Training Epoch: 14 [3072/9756]	Loss: 0.2681	LR: 0.020000
Training Epoch: 14 [3328/9756]	Loss: 0.2440	LR: 0.020000
Training Epoch: 14 [3584/9756]	Loss: 0.2582	LR: 0.020000
Training Epoch: 14 [3840/9756]	Loss: 0.2372	LR: 0.020000
Training Epoch: 14 [4096/9756]	Loss: 0.2478	LR: 0.020000
Training Epoch: 14 [4352/9756]	Loss: 0.2304	LR: 0.020000
Training Epoch: 14 [4608/9756]	Loss: 0.2205	LR: 0.020000
Training Epoch: 14 [4864/9756]	Loss: 0.1968	LR: 0.020000
Training Epoch: 14 [5120/9756]	Loss: 0.2523	LR: 0.020000
Training Epoch: 14 [5376/9756]	Loss: 0.2800	LR: 0.020000
Training Epoch: 14 [5632/9756]	Loss: 0.2178	LR: 0.020000
Training Epoch: 14 [5888/9756]	Loss: 0.2697	LR: 0.020000
Training Epoch: 14 [6144/9756]	Loss: 0.2440	LR: 0.020000
Training Epoch: 14 [6400/9756]	Loss: 0.2503	LR: 0.020000
Training Epoch: 14 [6656/9756]	Loss: 0.2543	LR: 0.020000
Training Epoch: 14 [6912/9756]	Loss: 0.2269	LR: 0.020000
Training Epoch: 14 [7168/9756]	Loss: 0.2379	LR: 0.020000
Training Epoch: 14 [7424/9756]	Loss: 0.2325	LR: 0.020000
Training Epoch: 14 [7680/9756]	Loss: 0.2852	LR: 0.020000
Training Epoch: 14 [7936/9756]	Loss: 0.2468	LR: 0.020000
Training Epoch: 14 [8192/9756]	Loss: 0.1798	LR: 0.020000
Training Epoch: 14 [8448/9756]	Loss: 0.1692	LR: 0.020000
Training Epoch: 14 [8704/9756]	Loss: 0.2430	LR: 0.020000
Training Epoch: 14 [8960/9756]	Loss: 0.2997	LR: 0.020000
Training Epoch: 14 [9216/9756]	Loss: 0.2858	LR: 0.020000
Training Epoch: 14 [9472/9756]	Loss: 0.1963	LR: 0.020000
Training Epoch: 14 [9728/9756]	Loss: 0.2427	LR: 0.020000
Training Epoch: 14 [9756/9756]	Loss: 0.1821	LR: 0.020000
Epoch 14 - Average Train Loss: 0.2465, Train Accuracy: 0.8942
Epoch 14 training time consumed: 140.83s
Evaluating Network.....
Test set: Epoch: 14, Average loss: 0.0030, Accuracy: 0.7366, Time consumed:8.02s
Training Epoch: 15 [256/9756]	Loss: 0.2781	LR: 0.020000
Training Epoch: 15 [512/9756]	Loss: 0.2467	LR: 0.020000
Training Epoch: 15 [768/9756]	Loss: 0.2494	LR: 0.020000
Training Epoch: 15 [1024/9756]	Loss: 0.2814	LR: 0.020000
Training Epoch: 15 [1280/9756]	Loss: 0.1777	LR: 0.020000
Training Epoch: 15 [1536/9756]	Loss: 0.2267	LR: 0.020000
Training Epoch: 15 [1792/9756]	Loss: 0.2877	LR: 0.020000
Training Epoch: 15 [2048/9756]	Loss: 0.2322	LR: 0.020000
Training Epoch: 15 [2304/9756]	Loss: 0.2595	LR: 0.020000
Training Epoch: 15 [2560/9756]	Loss: 0.1786	LR: 0.020000
Training Epoch: 15 [2816/9756]	Loss: 0.2510	LR: 0.020000
Training Epoch: 15 [3072/9756]	Loss: 0.3221	LR: 0.020000
Training Epoch: 15 [3328/9756]	Loss: 0.2127	LR: 0.020000
Training Epoch: 15 [3584/9756]	Loss: 0.2353	LR: 0.020000
Training Epoch: 15 [3840/9756]	Loss: 0.2005	LR: 0.020000
Training Epoch: 15 [4096/9756]	Loss: 0.2362	LR: 0.020000
Training Epoch: 15 [4352/9756]	Loss: 0.3090	LR: 0.020000
Training Epoch: 15 [4608/9756]	Loss: 0.2235	LR: 0.020000
Training Epoch: 15 [4864/9756]	Loss: 0.2969	LR: 0.020000
Training Epoch: 15 [5120/9756]	Loss: 0.2224	LR: 0.020000
Training Epoch: 15 [5376/9756]	Loss: 0.2175	LR: 0.020000
Training Epoch: 15 [5632/9756]	Loss: 0.3608	LR: 0.020000
Training Epoch: 15 [5888/9756]	Loss: 0.2455	LR: 0.020000
Training Epoch: 15 [6144/9756]	Loss: 0.2571	LR: 0.020000
Training Epoch: 15 [6400/9756]	Loss: 0.2595	LR: 0.020000
Training Epoch: 15 [6656/9756]	Loss: 0.2190	LR: 0.020000
Training Epoch: 15 [6912/9756]	Loss: 0.2524	LR: 0.020000
Training Epoch: 15 [7168/9756]	Loss: 0.2201	LR: 0.020000
Training Epoch: 15 [7424/9756]	Loss: 0.2165	LR: 0.020000
Training Epoch: 15 [7680/9756]	Loss: 0.2703	LR: 0.020000
Training Epoch: 15 [7936/9756]	Loss: 0.2217	LR: 0.020000
Training Epoch: 15 [8192/9756]	Loss: 0.2655	LR: 0.020000
Training Epoch: 15 [8448/9756]	Loss: 0.2306	LR: 0.020000
Training Epoch: 15 [8704/9756]	Loss: 0.1638	LR: 0.020000
Training Epoch: 15 [8960/9756]	Loss: 0.2118	LR: 0.020000
Training Epoch: 15 [9216/9756]	Loss: 0.1954	LR: 0.020000
Training Epoch: 15 [9472/9756]	Loss: 0.2624	LR: 0.020000
Training Epoch: 15 [9728/9756]	Loss: 0.2494	LR: 0.020000
Training Epoch: 15 [9756/9756]	Loss: 0.1803	LR: 0.020000
Epoch 15 - Average Train Loss: 0.2432, Train Accuracy: 0.8986
Epoch 15 training time consumed: 140.74s
Evaluating Network.....
Test set: Epoch: 15, Average loss: 0.0015, Accuracy: 0.8707, Time consumed:8.16s
Training Epoch: 16 [256/9756]	Loss: 0.2219	LR: 0.020000
Training Epoch: 16 [512/9756]	Loss: 0.1897	LR: 0.020000
Training Epoch: 16 [768/9756]	Loss: 0.1453	LR: 0.020000
Training Epoch: 16 [1024/9756]	Loss: 0.2471	LR: 0.020000
Training Epoch: 16 [1280/9756]	Loss: 0.1818	LR: 0.020000
Training Epoch: 16 [1536/9756]	Loss: 0.2264	LR: 0.020000
Training Epoch: 16 [1792/9756]	Loss: 0.2404	LR: 0.020000
Training Epoch: 16 [2048/9756]	Loss: 0.1814	LR: 0.020000
Training Epoch: 16 [2304/9756]	Loss: 0.2090	LR: 0.020000
Training Epoch: 16 [2560/9756]	Loss: 0.2048	LR: 0.020000
Training Epoch: 16 [2816/9756]	Loss: 0.2547	LR: 0.020000
Training Epoch: 16 [3072/9756]	Loss: 0.2206	LR: 0.020000
Training Epoch: 16 [3328/9756]	Loss: 0.2533	LR: 0.020000
Training Epoch: 16 [3584/9756]	Loss: 0.3953	LR: 0.020000
Training Epoch: 16 [3840/9756]	Loss: 0.1746	LR: 0.020000
Training Epoch: 16 [4096/9756]	Loss: 0.2084	LR: 0.020000
Training Epoch: 16 [4352/9756]	Loss: 0.1688	LR: 0.020000
Training Epoch: 16 [4608/9756]	Loss: 0.2228	LR: 0.020000
Training Epoch: 16 [4864/9756]	Loss: 0.2110	LR: 0.020000
Training Epoch: 16 [5120/9756]	Loss: 0.2257	LR: 0.020000
Training Epoch: 16 [5376/9756]	Loss: 0.2010	LR: 0.020000
Training Epoch: 16 [5632/9756]	Loss: 0.2395	LR: 0.020000
Training Epoch: 16 [5888/9756]	Loss: 0.1889	LR: 0.020000
Training Epoch: 16 [6144/9756]	Loss: 0.2111	LR: 0.020000
Training Epoch: 16 [6400/9756]	Loss: 0.2084	LR: 0.020000
Training Epoch: 16 [6656/9756]	Loss: 0.2560	LR: 0.020000
Training Epoch: 16 [6912/9756]	Loss: 0.2743	LR: 0.020000
Training Epoch: 16 [7168/9756]	Loss: 0.2222	LR: 0.020000
Training Epoch: 16 [7424/9756]	Loss: 0.2736	LR: 0.020000
Training Epoch: 16 [7680/9756]	Loss: 0.2255	LR: 0.020000
Training Epoch: 16 [7936/9756]	Loss: 0.2049	LR: 0.020000
Training Epoch: 16 [8192/9756]	Loss: 0.1676	LR: 0.020000
Training Epoch: 16 [8448/9756]	Loss: 0.1905	LR: 0.020000
Training Epoch: 16 [8704/9756]	Loss: 0.2290	LR: 0.020000
Training Epoch: 16 [8960/9756]	Loss: 0.2057	LR: 0.020000
Training Epoch: 16 [9216/9756]	Loss: 0.1955	LR: 0.020000
Training Epoch: 16 [9472/9756]	Loss: 0.2124	LR: 0.020000
Training Epoch: 16 [9728/9756]	Loss: 0.1948	LR: 0.020000
Training Epoch: 16 [9756/9756]	Loss: 0.1492	LR: 0.020000
Epoch 16 - Average Train Loss: 0.2178, Train Accuracy: 0.9096
Epoch 16 training time consumed: 140.59s
Evaluating Network.....
Test set: Epoch: 16, Average loss: 0.0013, Accuracy: 0.8828, Time consumed:8.23s
Training Epoch: 17 [256/9756]	Loss: 0.2363	LR: 0.020000
Training Epoch: 17 [512/9756]	Loss: 0.2088	LR: 0.020000
Training Epoch: 17 [768/9756]	Loss: 0.2291	LR: 0.020000
Training Epoch: 17 [1024/9756]	Loss: 0.1595	LR: 0.020000
Training Epoch: 17 [1280/9756]	Loss: 0.1807	LR: 0.020000
Training Epoch: 17 [1536/9756]	Loss: 0.1515	LR: 0.020000
Training Epoch: 17 [1792/9756]	Loss: 0.1572	LR: 0.020000
Training Epoch: 17 [2048/9756]	Loss: 0.1907	LR: 0.020000
Training Epoch: 17 [2304/9756]	Loss: 0.2274	LR: 0.020000
Training Epoch: 17 [2560/9756]	Loss: 0.1668	LR: 0.020000
Training Epoch: 17 [2816/9756]	Loss: 0.2397	LR: 0.020000
Training Epoch: 17 [3072/9756]	Loss: 0.2046	LR: 0.020000
Training Epoch: 17 [3328/9756]	Loss: 0.2108	LR: 0.020000
Training Epoch: 17 [3584/9756]	Loss: 0.3223	LR: 0.020000
Training Epoch: 17 [3840/9756]	Loss: 0.2229	LR: 0.020000
Training Epoch: 17 [4096/9756]	Loss: 0.2261	LR: 0.020000
Training Epoch: 17 [4352/9756]	Loss: 0.2204	LR: 0.020000
Training Epoch: 17 [4608/9756]	Loss: 0.1738	LR: 0.020000
Training Epoch: 17 [4864/9756]	Loss: 0.2147	LR: 0.020000
Training Epoch: 17 [5120/9756]	Loss: 0.2311	LR: 0.020000
Training Epoch: 17 [5376/9756]	Loss: 0.2065	LR: 0.020000
Training Epoch: 17 [5632/9756]	Loss: 0.1882	LR: 0.020000
Training Epoch: 17 [5888/9756]	Loss: 0.1915	LR: 0.020000
Training Epoch: 17 [6144/9756]	Loss: 0.2067	LR: 0.020000
Training Epoch: 17 [6400/9756]	Loss: 0.2306	LR: 0.020000
Training Epoch: 17 [6656/9756]	Loss: 0.1807	LR: 0.020000
Training Epoch: 17 [6912/9756]	Loss: 0.2896	LR: 0.020000
Training Epoch: 17 [7168/9756]	Loss: 0.1872	LR: 0.020000
Training Epoch: 17 [7424/9756]	Loss: 0.1878	LR: 0.020000
Training Epoch: 17 [7680/9756]	Loss: 0.2423	LR: 0.020000
Training Epoch: 17 [7936/9756]	Loss: 0.2819	LR: 0.020000
Training Epoch: 17 [8192/9756]	Loss: 0.2281	LR: 0.020000
Training Epoch: 17 [8448/9756]	Loss: 0.2449	LR: 0.020000
Training Epoch: 17 [8704/9756]	Loss: 0.2162	LR: 0.020000
Training Epoch: 17 [8960/9756]	Loss: 0.2348	LR: 0.020000
Training Epoch: 17 [9216/9756]	Loss: 0.1921	LR: 0.020000
Training Epoch: 17 [9472/9756]	Loss: 0.2457	LR: 0.020000
Training Epoch: 17 [9728/9756]	Loss: 0.1771	LR: 0.020000
Training Epoch: 17 [9756/9756]	Loss: 0.0988	LR: 0.020000
Epoch 17 - Average Train Loss: 0.2130, Train Accuracy: 0.9091
Epoch 17 training time consumed: 140.63s
Evaluating Network.....
Test set: Epoch: 17, Average loss: 0.0015, Accuracy: 0.8615, Time consumed:8.01s
Training Epoch: 18 [256/9756]	Loss: 0.1937	LR: 0.020000
Training Epoch: 18 [512/9756]	Loss: 0.2620	LR: 0.020000
Training Epoch: 18 [768/9756]	Loss: 0.1633	LR: 0.020000
Training Epoch: 18 [1024/9756]	Loss: 0.2466	LR: 0.020000
Training Epoch: 18 [1280/9756]	Loss: 0.1998	LR: 0.020000
Training Epoch: 18 [1536/9756]	Loss: 0.2262	LR: 0.020000
Training Epoch: 18 [1792/9756]	Loss: 0.2222	LR: 0.020000
Training Epoch: 18 [2048/9756]	Loss: 0.2515	LR: 0.020000
Training Epoch: 18 [2304/9756]	Loss: 0.2107	LR: 0.020000
Training Epoch: 18 [2560/9756]	Loss: 0.1479	LR: 0.020000
Training Epoch: 18 [2816/9756]	Loss: 0.2223	LR: 0.020000
Training Epoch: 18 [3072/9756]	Loss: 0.2920	LR: 0.020000
Training Epoch: 18 [3328/9756]	Loss: 0.1344	LR: 0.020000
Training Epoch: 18 [3584/9756]	Loss: 0.1504	LR: 0.020000
Training Epoch: 18 [3840/9756]	Loss: 0.1901	LR: 0.020000
Training Epoch: 18 [4096/9756]	Loss: 0.2025	LR: 0.020000
Training Epoch: 18 [4352/9756]	Loss: 0.1756	LR: 0.020000
Training Epoch: 18 [4608/9756]	Loss: 0.1489	LR: 0.020000
Training Epoch: 18 [4864/9756]	Loss: 0.1893	LR: 0.020000
Training Epoch: 18 [5120/9756]	Loss: 0.1993	LR: 0.020000
Training Epoch: 18 [5376/9756]	Loss: 0.1595	LR: 0.020000
Training Epoch: 18 [5632/9756]	Loss: 0.1885	LR: 0.020000
Training Epoch: 18 [5888/9756]	Loss: 0.1631	LR: 0.020000
Training Epoch: 18 [6144/9756]	Loss: 0.2129	LR: 0.020000
Training Epoch: 18 [6400/9756]	Loss: 0.2196	LR: 0.020000
Training Epoch: 18 [6656/9756]	Loss: 0.1967	LR: 0.020000
Training Epoch: 18 [6912/9756]	Loss: 0.2092	LR: 0.020000
Training Epoch: 18 [7168/9756]	Loss: 0.2308	LR: 0.020000
Training Epoch: 18 [7424/9756]	Loss: 0.1452	LR: 0.020000
Training Epoch: 18 [7680/9756]	Loss: 0.1984	LR: 0.020000
Training Epoch: 18 [7936/9756]	Loss: 0.2087	LR: 0.020000
Training Epoch: 18 [8192/9756]	Loss: 0.1339	LR: 0.020000
Training Epoch: 18 [8448/9756]	Loss: 0.1885	LR: 0.020000
Training Epoch: 18 [8704/9756]	Loss: 0.1429	LR: 0.020000
Training Epoch: 18 [8960/9756]	Loss: 0.1426	LR: 0.020000
Training Epoch: 18 [9216/9756]	Loss: 0.1713	LR: 0.020000
Training Epoch: 18 [9472/9756]	Loss: 0.1797	LR: 0.020000
Training Epoch: 18 [9728/9756]	Loss: 0.1684	LR: 0.020000
Training Epoch: 18 [9756/9756]	Loss: 0.1654	LR: 0.020000
Epoch 18 - Average Train Loss: 0.1917, Train Accuracy: 0.9222
Epoch 18 training time consumed: 140.93s
Evaluating Network.....
Test set: Epoch: 18, Average loss: 0.0031, Accuracy: 0.7308, Time consumed:7.90s
Training Epoch: 19 [256/9756]	Loss: 0.1903	LR: 0.020000
Training Epoch: 19 [512/9756]	Loss: 0.1476	LR: 0.020000
Training Epoch: 19 [768/9756]	Loss: 0.1777	LR: 0.020000
Training Epoch: 19 [1024/9756]	Loss: 0.1443	LR: 0.020000
Training Epoch: 19 [1280/9756]	Loss: 0.1584	LR: 0.020000
Training Epoch: 19 [1536/9756]	Loss: 0.1980	LR: 0.020000
Training Epoch: 19 [1792/9756]	Loss: 0.1965	LR: 0.020000
Training Epoch: 19 [2048/9756]	Loss: 0.1992	LR: 0.020000
Training Epoch: 19 [2304/9756]	Loss: 0.2132	LR: 0.020000
Training Epoch: 19 [2560/9756]	Loss: 0.1399	LR: 0.020000
Training Epoch: 19 [2816/9756]	Loss: 0.1753	LR: 0.020000
Training Epoch: 19 [3072/9756]	Loss: 0.1621	LR: 0.020000
Training Epoch: 19 [3328/9756]	Loss: 0.1877	LR: 0.020000
Training Epoch: 19 [3584/9756]	Loss: 0.2210	LR: 0.020000
Training Epoch: 19 [3840/9756]	Loss: 0.1838	LR: 0.020000
Training Epoch: 19 [4096/9756]	Loss: 0.1808	LR: 0.020000
Training Epoch: 19 [4352/9756]	Loss: 0.1639	LR: 0.020000
Training Epoch: 19 [4608/9756]	Loss: 0.1334	LR: 0.020000
Training Epoch: 19 [4864/9756]	Loss: 0.1846	LR: 0.020000
Training Epoch: 19 [5120/9756]	Loss: 0.2434	LR: 0.020000
Training Epoch: 19 [5376/9756]	Loss: 0.1539	LR: 0.020000
Training Epoch: 19 [5632/9756]	Loss: 0.1592	LR: 0.020000
Training Epoch: 19 [5888/9756]	Loss: 0.1698	LR: 0.020000
Training Epoch: 19 [6144/9756]	Loss: 0.1870	LR: 0.020000
Training Epoch: 19 [6400/9756]	Loss: 0.1595	LR: 0.020000
Training Epoch: 19 [6656/9756]	Loss: 0.2415	LR: 0.020000
Training Epoch: 19 [6912/9756]	Loss: 0.2261	LR: 0.020000
Training Epoch: 19 [7168/9756]	Loss: 0.2401	LR: 0.020000
Training Epoch: 19 [7424/9756]	Loss: 0.1711	LR: 0.020000
Training Epoch: 19 [7680/9756]	Loss: 0.2470	LR: 0.020000
Training Epoch: 19 [7936/9756]	Loss: 0.1695	LR: 0.020000
Training Epoch: 19 [8192/9756]	Loss: 0.1861	LR: 0.020000
Training Epoch: 19 [8448/9756]	Loss: 0.2291	LR: 0.020000
Training Epoch: 19 [8704/9756]	Loss: 0.2048	LR: 0.020000
Training Epoch: 19 [8960/9756]	Loss: 0.1598	LR: 0.020000
Training Epoch: 19 [9216/9756]	Loss: 0.1795	LR: 0.020000
Training Epoch: 19 [9472/9756]	Loss: 0.2315	LR: 0.020000
Training Epoch: 19 [9728/9756]	Loss: 0.2079	LR: 0.020000
Training Epoch: 19 [9756/9756]	Loss: 0.1862	LR: 0.020000
Epoch 19 - Average Train Loss: 0.1875, Train Accuracy: 0.9234
Epoch 19 training time consumed: 140.52s
Evaluating Network.....
Test set: Epoch: 19, Average loss: 0.0018, Accuracy: 0.8702, Time consumed:8.06s
Training Epoch: 20 [256/9756]	Loss: 0.1889	LR: 0.004000
Training Epoch: 20 [512/9756]	Loss: 0.1624	LR: 0.004000
Training Epoch: 20 [768/9756]	Loss: 0.1634	LR: 0.004000
Training Epoch: 20 [1024/9756]	Loss: 0.1585	LR: 0.004000
Training Epoch: 20 [1280/9756]	Loss: 0.1751	LR: 0.004000
Training Epoch: 20 [1536/9756]	Loss: 0.1711	LR: 0.004000
Training Epoch: 20 [1792/9756]	Loss: 0.1522	LR: 0.004000
Training Epoch: 20 [2048/9756]	Loss: 0.2181	LR: 0.004000
Training Epoch: 20 [2304/9756]	Loss: 0.1756	LR: 0.004000
Training Epoch: 20 [2560/9756]	Loss: 0.1844	LR: 0.004000
Training Epoch: 20 [2816/9756]	Loss: 0.2024	LR: 0.004000
Training Epoch: 20 [3072/9756]	Loss: 0.1462	LR: 0.004000
Training Epoch: 20 [3328/9756]	Loss: 0.1386	LR: 0.004000
Training Epoch: 20 [3584/9756]	Loss: 0.1248	LR: 0.004000
Training Epoch: 20 [3840/9756]	Loss: 0.1770	LR: 0.004000
Training Epoch: 20 [4096/9756]	Loss: 0.1509	LR: 0.004000
Training Epoch: 20 [4352/9756]	Loss: 0.2197	LR: 0.004000
Training Epoch: 20 [4608/9756]	Loss: 0.1650	LR: 0.004000
Training Epoch: 20 [4864/9756]	Loss: 0.1242	LR: 0.004000
Training Epoch: 20 [5120/9756]	Loss: 0.1407	LR: 0.004000
Training Epoch: 20 [5376/9756]	Loss: 0.1828	LR: 0.004000
Training Epoch: 20 [5632/9756]	Loss: 0.1786	LR: 0.004000
Training Epoch: 20 [5888/9756]	Loss: 0.1939	LR: 0.004000
Training Epoch: 20 [6144/9756]	Loss: 0.1661	LR: 0.004000
Training Epoch: 20 [6400/9756]	Loss: 0.1582	LR: 0.004000
Training Epoch: 20 [6656/9756]	Loss: 0.2172	LR: 0.004000
Training Epoch: 20 [6912/9756]	Loss: 0.1848	LR: 0.004000
Training Epoch: 20 [7168/9756]	Loss: 0.1610	LR: 0.004000
Training Epoch: 20 [7424/9756]	Loss: 0.1758	LR: 0.004000
Training Epoch: 20 [7680/9756]	Loss: 0.1613	LR: 0.004000
Training Epoch: 20 [7936/9756]	Loss: 0.1954	LR: 0.004000
Training Epoch: 20 [8192/9756]	Loss: 0.1602	LR: 0.004000
Training Epoch: 20 [8448/9756]	Loss: 0.1366	LR: 0.004000
Training Epoch: 20 [8704/9756]	Loss: 0.1989	LR: 0.004000
Training Epoch: 20 [8960/9756]	Loss: 0.1764	LR: 0.004000
Training Epoch: 20 [9216/9756]	Loss: 0.1477	LR: 0.004000
Training Epoch: 20 [9472/9756]	Loss: 0.1706	LR: 0.004000
Training Epoch: 20 [9728/9756]	Loss: 0.1732	LR: 0.004000
Training Epoch: 20 [9756/9756]	Loss: 0.1517	LR: 0.004000
Epoch 20 - Average Train Loss: 0.1704, Train Accuracy: 0.9306
Epoch 20 training time consumed: 140.73s
Evaluating Network.....
Test set: Epoch: 20, Average loss: 0.0008, Accuracy: 0.9220, Time consumed:8.22s
Saving weights file to checkpoint/retrain/ResNet18/Saturday_26_July_2025_01h_54m_23s/ResNet18-MUCAC-seed4-ret25-20-best.pth
Training Epoch: 21 [256/9756]	Loss: 0.1740	LR: 0.004000
Training Epoch: 21 [512/9756]	Loss: 0.2003	LR: 0.004000
Training Epoch: 21 [768/9756]	Loss: 0.1396	LR: 0.004000
Training Epoch: 21 [1024/9756]	Loss: 0.2153	LR: 0.004000
Training Epoch: 21 [1280/9756]	Loss: 0.1589	LR: 0.004000
Training Epoch: 21 [1536/9756]	Loss: 0.1645	LR: 0.004000
Training Epoch: 21 [1792/9756]	Loss: 0.1448	LR: 0.004000
Training Epoch: 21 [2048/9756]	Loss: 0.1505	LR: 0.004000
Training Epoch: 21 [2304/9756]	Loss: 0.1594	LR: 0.004000
Training Epoch: 21 [2560/9756]	Loss: 0.1460	LR: 0.004000
Training Epoch: 21 [2816/9756]	Loss: 0.1688	LR: 0.004000
Training Epoch: 21 [3072/9756]	Loss: 0.1328	LR: 0.004000
Training Epoch: 21 [3328/9756]	Loss: 0.1883	LR: 0.004000
Training Epoch: 21 [3584/9756]	Loss: 0.1706	LR: 0.004000
Training Epoch: 21 [3840/9756]	Loss: 0.1739	LR: 0.004000
Training Epoch: 21 [4096/9756]	Loss: 0.1671	LR: 0.004000
Training Epoch: 21 [4352/9756]	Loss: 0.1424	LR: 0.004000
Training Epoch: 21 [4608/9756]	Loss: 0.1557	LR: 0.004000
Training Epoch: 21 [4864/9756]	Loss: 0.1374	LR: 0.004000
Training Epoch: 21 [5120/9756]	Loss: 0.1317	LR: 0.004000
Training Epoch: 21 [5376/9756]	Loss: 0.1279	LR: 0.004000
Training Epoch: 21 [5632/9756]	Loss: 0.1271	LR: 0.004000
Training Epoch: 21 [5888/9756]	Loss: 0.1753	LR: 0.004000
Training Epoch: 21 [6144/9756]	Loss: 0.1439	LR: 0.004000
Training Epoch: 21 [6400/9756]	Loss: 0.1156	LR: 0.004000
Training Epoch: 21 [6656/9756]	Loss: 0.2073	LR: 0.004000
Training Epoch: 21 [6912/9756]	Loss: 0.1613	LR: 0.004000
Training Epoch: 21 [7168/9756]	Loss: 0.1193	LR: 0.004000
Training Epoch: 21 [7424/9756]	Loss: 0.1830	LR: 0.004000
Training Epoch: 21 [7680/9756]	Loss: 0.1362	LR: 0.004000
Training Epoch: 21 [7936/9756]	Loss: 0.1811	LR: 0.004000
Training Epoch: 21 [8192/9756]	Loss: 0.1517	LR: 0.004000
Training Epoch: 21 [8448/9756]	Loss: 0.1467	LR: 0.004000
Training Epoch: 21 [8704/9756]	Loss: 0.1445	LR: 0.004000
Training Epoch: 21 [8960/9756]	Loss: 0.1956	LR: 0.004000
Training Epoch: 21 [9216/9756]	Loss: 0.1463	LR: 0.004000
Training Epoch: 21 [9472/9756]	Loss: 0.1326	LR: 0.004000
Training Epoch: 21 [9728/9756]	Loss: 0.1557	LR: 0.004000
Training Epoch: 21 [9756/9756]	Loss: 0.1207	LR: 0.004000
Epoch 21 - Average Train Loss: 0.1571, Train Accuracy: 0.9349
Epoch 21 training time consumed: 140.82s
Evaluating Network.....
Test set: Epoch: 21, Average loss: 0.0006, Accuracy: 0.9419, Time consumed:7.86s
Saving weights file to checkpoint/retrain/ResNet18/Saturday_26_July_2025_01h_54m_23s/ResNet18-MUCAC-seed4-ret25-21-best.pth
Training Epoch: 22 [256/9756]	Loss: 0.1472	LR: 0.004000
Training Epoch: 22 [512/9756]	Loss: 0.1550	LR: 0.004000
Training Epoch: 22 [768/9756]	Loss: 0.1306	LR: 0.004000
Training Epoch: 22 [1024/9756]	Loss: 0.2028	LR: 0.004000
Training Epoch: 22 [1280/9756]	Loss: 0.1850	LR: 0.004000
Training Epoch: 22 [1536/9756]	Loss: 0.1651	LR: 0.004000
Training Epoch: 22 [1792/9756]	Loss: 0.2151	LR: 0.004000
Training Epoch: 22 [2048/9756]	Loss: 0.1681	LR: 0.004000
Training Epoch: 22 [2304/9756]	Loss: 0.1879	LR: 0.004000
Training Epoch: 22 [2560/9756]	Loss: 0.1302	LR: 0.004000
Training Epoch: 22 [2816/9756]	Loss: 0.1879	LR: 0.004000
Training Epoch: 22 [3072/9756]	Loss: 0.2011	LR: 0.004000
Training Epoch: 22 [3328/9756]	Loss: 0.1380	LR: 0.004000
Training Epoch: 22 [3584/9756]	Loss: 0.1324	LR: 0.004000
Training Epoch: 22 [3840/9756]	Loss: 0.1354	LR: 0.004000
Training Epoch: 22 [4096/9756]	Loss: 0.1450	LR: 0.004000
Training Epoch: 22 [4352/9756]	Loss: 0.1611	LR: 0.004000
Training Epoch: 22 [4608/9756]	Loss: 0.1215	LR: 0.004000
Training Epoch: 22 [4864/9756]	Loss: 0.1324	LR: 0.004000
Training Epoch: 22 [5120/9756]	Loss: 0.1275	LR: 0.004000
Training Epoch: 22 [5376/9756]	Loss: 0.1178	LR: 0.004000
Training Epoch: 22 [5632/9756]	Loss: 0.1729	LR: 0.004000
Training Epoch: 22 [5888/9756]	Loss: 0.1569	LR: 0.004000
Training Epoch: 22 [6144/9756]	Loss: 0.1979	LR: 0.004000
Training Epoch: 22 [6400/9756]	Loss: 0.1594	LR: 0.004000
Training Epoch: 22 [6656/9756]	Loss: 0.1082	LR: 0.004000
Training Epoch: 22 [6912/9756]	Loss: 0.1424	LR: 0.004000
Training Epoch: 22 [7168/9756]	Loss: 0.1152	LR: 0.004000
Training Epoch: 22 [7424/9756]	Loss: 0.1304	LR: 0.004000
Training Epoch: 22 [7680/9756]	Loss: 0.1395	LR: 0.004000
Training Epoch: 22 [7936/9756]	Loss: 0.1266	LR: 0.004000
Training Epoch: 22 [8192/9756]	Loss: 0.1433	LR: 0.004000
Training Epoch: 22 [8448/9756]	Loss: 0.1736	LR: 0.004000
Training Epoch: 22 [8704/9756]	Loss: 0.1219	LR: 0.004000
Training Epoch: 22 [8960/9756]	Loss: 0.1254	LR: 0.004000
Training Epoch: 22 [9216/9756]	Loss: 0.1666	LR: 0.004000
Training Epoch: 22 [9472/9756]	Loss: 0.1978	LR: 0.004000
Training Epoch: 22 [9728/9756]	Loss: 0.1451	LR: 0.004000
Training Epoch: 22 [9756/9756]	Loss: 0.1463	LR: 0.004000
Epoch 22 - Average Train Loss: 0.1529, Train Accuracy: 0.9367
Epoch 22 training time consumed: 141.15s
Evaluating Network.....
Test set: Epoch: 22, Average loss: 0.0007, Accuracy: 0.9370, Time consumed:8.00s
Training Epoch: 23 [256/9756]	Loss: 0.1911	LR: 0.004000
Training Epoch: 23 [512/9756]	Loss: 0.1406	LR: 0.004000
Training Epoch: 23 [768/9756]	Loss: 0.1229	LR: 0.004000
Training Epoch: 23 [1024/9756]	Loss: 0.1573	LR: 0.004000
Training Epoch: 23 [1280/9756]	Loss: 0.1055	LR: 0.004000
Training Epoch: 23 [1536/9756]	Loss: 0.1926	LR: 0.004000
Training Epoch: 23 [1792/9756]	Loss: 0.1499	LR: 0.004000
Training Epoch: 23 [2048/9756]	Loss: 0.1173	LR: 0.004000
Training Epoch: 23 [2304/9756]	Loss: 0.1062	LR: 0.004000
Training Epoch: 23 [2560/9756]	Loss: 0.1520	LR: 0.004000
Training Epoch: 23 [2816/9756]	Loss: 0.1980	LR: 0.004000
Training Epoch: 23 [3072/9756]	Loss: 0.2084	LR: 0.004000
Training Epoch: 23 [3328/9756]	Loss: 0.1150	LR: 0.004000
Training Epoch: 23 [3584/9756]	Loss: 0.1657	LR: 0.004000
Training Epoch: 23 [3840/9756]	Loss: 0.1616	LR: 0.004000
Training Epoch: 23 [4096/9756]	Loss: 0.1138	LR: 0.004000
Training Epoch: 23 [4352/9756]	Loss: 0.1832	LR: 0.004000
Training Epoch: 23 [4608/9756]	Loss: 0.1725	LR: 0.004000
Training Epoch: 23 [4864/9756]	Loss: 0.1417	LR: 0.004000
Training Epoch: 23 [5120/9756]	Loss: 0.1621	LR: 0.004000
Training Epoch: 23 [5376/9756]	Loss: 0.1279	LR: 0.004000
Training Epoch: 23 [5632/9756]	Loss: 0.1507	LR: 0.004000
Training Epoch: 23 [5888/9756]	Loss: 0.2738	LR: 0.004000
Training Epoch: 23 [6144/9756]	Loss: 0.1267	LR: 0.004000
Training Epoch: 23 [6400/9756]	Loss: 0.1523	LR: 0.004000
Training Epoch: 23 [6656/9756]	Loss: 0.1153	LR: 0.004000
Training Epoch: 23 [6912/9756]	Loss: 0.1586	LR: 0.004000
Training Epoch: 23 [7168/9756]	Loss: 0.1114	LR: 0.004000
Training Epoch: 23 [7424/9756]	Loss: 0.1644	LR: 0.004000
Training Epoch: 23 [7680/9756]	Loss: 0.1122	LR: 0.004000
Training Epoch: 23 [7936/9756]	Loss: 0.1697	LR: 0.004000
Training Epoch: 23 [8192/9756]	Loss: 0.1528	LR: 0.004000
Training Epoch: 23 [8448/9756]	Loss: 0.1446	LR: 0.004000
Training Epoch: 23 [8704/9756]	Loss: 0.1734	LR: 0.004000
Training Epoch: 23 [8960/9756]	Loss: 0.1338	LR: 0.004000
Training Epoch: 23 [9216/9756]	Loss: 0.1936	LR: 0.004000
Training Epoch: 23 [9472/9756]	Loss: 0.1515	LR: 0.004000
Training Epoch: 23 [9728/9756]	Loss: 0.1493	LR: 0.004000
Training Epoch: 23 [9756/9756]	Loss: 0.0409	LR: 0.004000
Epoch 23 - Average Train Loss: 0.1528, Train Accuracy: 0.9374
Epoch 23 training time consumed: 140.44s
Evaluating Network.....
Test set: Epoch: 23, Average loss: 0.0007, Accuracy: 0.9361, Time consumed:8.05s
Training Epoch: 24 [256/9756]	Loss: 0.1354	LR: 0.004000
Training Epoch: 24 [512/9756]	Loss: 0.1700	LR: 0.004000
Training Epoch: 24 [768/9756]	Loss: 0.1301	LR: 0.004000
Training Epoch: 24 [1024/9756]	Loss: 0.1413	LR: 0.004000
Training Epoch: 24 [1280/9756]	Loss: 0.1883	LR: 0.004000
Training Epoch: 24 [1536/9756]	Loss: 0.1474	LR: 0.004000
Training Epoch: 24 [1792/9756]	Loss: 0.1029	LR: 0.004000
Training Epoch: 24 [2048/9756]	Loss: 0.1327	LR: 0.004000
Training Epoch: 24 [2304/9756]	Loss: 0.1474	LR: 0.004000
Training Epoch: 24 [2560/9756]	Loss: 0.1069	LR: 0.004000
Training Epoch: 24 [2816/9756]	Loss: 0.1754	LR: 0.004000
Training Epoch: 24 [3072/9756]	Loss: 0.1492	LR: 0.004000
Training Epoch: 24 [3328/9756]	Loss: 0.1828	LR: 0.004000
Training Epoch: 24 [3584/9756]	Loss: 0.1019	LR: 0.004000
Training Epoch: 24 [3840/9756]	Loss: 0.1315	LR: 0.004000
Training Epoch: 24 [4096/9756]	Loss: 0.1278	LR: 0.004000
Training Epoch: 24 [4352/9756]	Loss: 0.1616	LR: 0.004000
Training Epoch: 24 [4608/9756]	Loss: 0.1411	LR: 0.004000
Training Epoch: 24 [4864/9756]	Loss: 0.1027	LR: 0.004000
Training Epoch: 24 [5120/9756]	Loss: 0.1560	LR: 0.004000
Training Epoch: 24 [5376/9756]	Loss: 0.1267	LR: 0.004000
Training Epoch: 24 [5632/9756]	Loss: 0.1616	LR: 0.004000
Training Epoch: 24 [5888/9756]	Loss: 0.1026	LR: 0.004000
Training Epoch: 24 [6144/9756]	Loss: 0.1181	LR: 0.004000
Training Epoch: 24 [6400/9756]	Loss: 0.1553	LR: 0.004000
Training Epoch: 24 [6656/9756]	Loss: 0.1518	LR: 0.004000
Training Epoch: 24 [6912/9756]	Loss: 0.1216	LR: 0.004000
Training Epoch: 24 [7168/9756]	Loss: 0.1809	LR: 0.004000
Training Epoch: 24 [7424/9756]	Loss: 0.1125	LR: 0.004000
Training Epoch: 24 [7680/9756]	Loss: 0.1621	LR: 0.004000
Training Epoch: 24 [7936/9756]	Loss: 0.1349	LR: 0.004000
Training Epoch: 24 [8192/9756]	Loss: 0.1893	LR: 0.004000
Training Epoch: 24 [8448/9756]	Loss: 0.1268	LR: 0.004000
Training Epoch: 24 [8704/9756]	Loss: 0.1945	LR: 0.004000
Training Epoch: 24 [8960/9756]	Loss: 0.1495	LR: 0.004000
Training Epoch: 24 [9216/9756]	Loss: 0.1696	LR: 0.004000
Training Epoch: 24 [9472/9756]	Loss: 0.1444	LR: 0.004000
Training Epoch: 24 [9728/9756]	Loss: 0.1438	LR: 0.004000
Training Epoch: 24 [9756/9756]	Loss: 0.3995	LR: 0.004000
Epoch 24 - Average Train Loss: 0.1449, Train Accuracy: 0.9413
Epoch 24 training time consumed: 140.46s
Evaluating Network.....
Test set: Epoch: 24, Average loss: 0.0006, Accuracy: 0.9404, Time consumed:8.05s
Training Epoch: 25 [256/9756]	Loss: 0.1234	LR: 0.004000
Training Epoch: 25 [512/9756]	Loss: 0.0864	LR: 0.004000
Training Epoch: 25 [768/9756]	Loss: 0.1690	LR: 0.004000
Training Epoch: 25 [1024/9756]	Loss: 0.1231	LR: 0.004000
Training Epoch: 25 [1280/9756]	Loss: 0.1493	LR: 0.004000
Training Epoch: 25 [1536/9756]	Loss: 0.1957	LR: 0.004000
Training Epoch: 25 [1792/9756]	Loss: 0.1579	LR: 0.004000
Training Epoch: 25 [2048/9756]	Loss: 0.1590	LR: 0.004000
Training Epoch: 25 [2304/9756]	Loss: 0.1760	LR: 0.004000
Training Epoch: 25 [2560/9756]	Loss: 0.1507	LR: 0.004000
Training Epoch: 25 [2816/9756]	Loss: 0.0986	LR: 0.004000
Training Epoch: 25 [3072/9756]	Loss: 0.1313	LR: 0.004000
Training Epoch: 25 [3328/9756]	Loss: 0.1405	LR: 0.004000
Training Epoch: 25 [3584/9756]	Loss: 0.1446	LR: 0.004000
Training Epoch: 25 [3840/9756]	Loss: 0.1638	LR: 0.004000
Training Epoch: 25 [4096/9756]	Loss: 0.1302	LR: 0.004000
Training Epoch: 25 [4352/9756]	Loss: 0.1214	LR: 0.004000
Training Epoch: 25 [4608/9756]	Loss: 0.1872	LR: 0.004000
Training Epoch: 25 [4864/9756]	Loss: 0.1436	LR: 0.004000
Training Epoch: 25 [5120/9756]	Loss: 0.1329	LR: 0.004000
Training Epoch: 25 [5376/9756]	Loss: 0.1214	LR: 0.004000
Training Epoch: 25 [5632/9756]	Loss: 0.1438	LR: 0.004000
Training Epoch: 25 [5888/9756]	Loss: 0.1495	LR: 0.004000
Training Epoch: 25 [6144/9756]	Loss: 0.1485	LR: 0.004000
Training Epoch: 25 [6400/9756]	Loss: 0.1669	LR: 0.004000
Training Epoch: 25 [6656/9756]	Loss: 0.1430	LR: 0.004000
Training Epoch: 25 [6912/9756]	Loss: 0.1460	LR: 0.004000
Training Epoch: 25 [7168/9756]	Loss: 0.2083	LR: 0.004000
Training Epoch: 25 [7424/9756]	Loss: 0.1904	LR: 0.004000
Training Epoch: 25 [7680/9756]	Loss: 0.1551	LR: 0.004000
Training Epoch: 25 [7936/9756]	Loss: 0.1360	LR: 0.004000
Training Epoch: 25 [8192/9756]	Loss: 0.1200	LR: 0.004000
Training Epoch: 25 [8448/9756]	Loss: 0.1285	LR: 0.004000
Training Epoch: 25 [8704/9756]	Loss: 0.1081	LR: 0.004000
Training Epoch: 25 [8960/9756]	Loss: 0.1816	LR: 0.004000
Training Epoch: 25 [9216/9756]	Loss: 0.1169	LR: 0.004000
Training Epoch: 25 [9472/9756]	Loss: 0.1750	LR: 0.004000
Training Epoch: 25 [9728/9756]	Loss: 0.1476	LR: 0.004000
Training Epoch: 25 [9756/9756]	Loss: 0.0502	LR: 0.004000
Epoch 25 - Average Train Loss: 0.1463, Train Accuracy: 0.9412
Epoch 25 training time consumed: 139.97s
Evaluating Network.....
Test set: Epoch: 25, Average loss: 0.0006, Accuracy: 0.9390, Time consumed:8.11s
Training Epoch: 26 [256/9756]	Loss: 0.2121	LR: 0.004000
Training Epoch: 26 [512/9756]	Loss: 0.1518	LR: 0.004000
Training Epoch: 26 [768/9756]	Loss: 0.0929	LR: 0.004000
Training Epoch: 26 [1024/9756]	Loss: 0.1170	LR: 0.004000
Training Epoch: 26 [1280/9756]	Loss: 0.1301	LR: 0.004000
Training Epoch: 26 [1536/9756]	Loss: 0.1327	LR: 0.004000
Training Epoch: 26 [1792/9756]	Loss: 0.0932	LR: 0.004000
Training Epoch: 26 [2048/9756]	Loss: 0.1387	LR: 0.004000
Training Epoch: 26 [2304/9756]	Loss: 0.1658	LR: 0.004000
Training Epoch: 26 [2560/9756]	Loss: 0.1391	LR: 0.004000
Training Epoch: 26 [2816/9756]	Loss: 0.1601	LR: 0.004000
Training Epoch: 26 [3072/9756]	Loss: 0.1388	LR: 0.004000
Training Epoch: 26 [3328/9756]	Loss: 0.1645	LR: 0.004000
Training Epoch: 26 [3584/9756]	Loss: 0.1720	LR: 0.004000
Training Epoch: 26 [3840/9756]	Loss: 0.1388	LR: 0.004000
Training Epoch: 26 [4096/9756]	Loss: 0.1342	LR: 0.004000
Training Epoch: 26 [4352/9756]	Loss: 0.1337	LR: 0.004000
Training Epoch: 26 [4608/9756]	Loss: 0.1704	LR: 0.004000
Training Epoch: 26 [4864/9756]	Loss: 0.1508	LR: 0.004000
Training Epoch: 26 [5120/9756]	Loss: 0.1545	LR: 0.004000
Training Epoch: 26 [5376/9756]	Loss: 0.1439	LR: 0.004000
Training Epoch: 26 [5632/9756]	Loss: 0.1490	LR: 0.004000
Training Epoch: 26 [5888/9756]	Loss: 0.1387	LR: 0.004000
Training Epoch: 26 [6144/9756]	Loss: 0.1249	LR: 0.004000
Training Epoch: 26 [6400/9756]	Loss: 0.1159	LR: 0.004000
Training Epoch: 26 [6656/9756]	Loss: 0.1132	LR: 0.004000
Training Epoch: 26 [6912/9756]	Loss: 0.1166	LR: 0.004000
Training Epoch: 26 [7168/9756]	Loss: 0.1786	LR: 0.004000
Training Epoch: 26 [7424/9756]	Loss: 0.1441	LR: 0.004000
Training Epoch: 26 [7680/9756]	Loss: 0.1584	LR: 0.004000
Training Epoch: 26 [7936/9756]	Loss: 0.0700	LR: 0.004000
Training Epoch: 26 [8192/9756]	Loss: 0.1120	LR: 0.004000
Training Epoch: 26 [8448/9756]	Loss: 0.1410	LR: 0.004000
Training Epoch: 26 [8704/9756]	Loss: 0.1812	LR: 0.004000
Training Epoch: 26 [8960/9756]	Loss: 0.2023	LR: 0.004000
Training Epoch: 26 [9216/9756]	Loss: 0.1320	LR: 0.004000
Training Epoch: 26 [9472/9756]	Loss: 0.1250	LR: 0.004000
Training Epoch: 26 [9728/9756]	Loss: 0.1635	LR: 0.004000
Training Epoch: 26 [9756/9756]	Loss: 0.0998	LR: 0.004000
Epoch 26 - Average Train Loss: 0.1420, Train Accuracy: 0.9415
Epoch 26 training time consumed: 140.62s
Evaluating Network.....
Test set: Epoch: 26, Average loss: 0.0008, Accuracy: 0.9332, Time consumed:7.90s
Training Epoch: 27 [256/9756]	Loss: 0.1450	LR: 0.004000
Training Epoch: 27 [512/9756]	Loss: 0.1272	LR: 0.004000
Training Epoch: 27 [768/9756]	Loss: 0.1233	LR: 0.004000
Training Epoch: 27 [1024/9756]	Loss: 0.1498	LR: 0.004000
Training Epoch: 27 [1280/9756]	Loss: 0.1482	LR: 0.004000
Training Epoch: 27 [1536/9756]	Loss: 0.1789	LR: 0.004000
Training Epoch: 27 [1792/9756]	Loss: 0.1735	LR: 0.004000
Training Epoch: 27 [2048/9756]	Loss: 0.1520	LR: 0.004000
Training Epoch: 27 [2304/9756]	Loss: 0.1774	LR: 0.004000
Training Epoch: 27 [2560/9756]	Loss: 0.1281	LR: 0.004000
Training Epoch: 27 [2816/9756]	Loss: 0.1178	LR: 0.004000
Training Epoch: 27 [3072/9756]	Loss: 0.1627	LR: 0.004000
Training Epoch: 27 [3328/9756]	Loss: 0.1302	LR: 0.004000
Training Epoch: 27 [3584/9756]	Loss: 0.1468	LR: 0.004000
Training Epoch: 27 [3840/9756]	Loss: 0.1313	LR: 0.004000
Training Epoch: 27 [4096/9756]	Loss: 0.1061	LR: 0.004000
Training Epoch: 27 [4352/9756]	Loss: 0.1512	LR: 0.004000
Training Epoch: 27 [4608/9756]	Loss: 0.1363	LR: 0.004000
Training Epoch: 27 [4864/9756]	Loss: 0.0936	LR: 0.004000
Training Epoch: 27 [5120/9756]	Loss: 0.1317	LR: 0.004000
Training Epoch: 27 [5376/9756]	Loss: 0.1724	LR: 0.004000
Training Epoch: 27 [5632/9756]	Loss: 0.1778	LR: 0.004000
Training Epoch: 27 [5888/9756]	Loss: 0.1150	LR: 0.004000
Training Epoch: 27 [6144/9756]	Loss: 0.1291	LR: 0.004000
Training Epoch: 27 [6400/9756]	Loss: 0.1175	LR: 0.004000
Training Epoch: 27 [6656/9756]	Loss: 0.1249	LR: 0.004000
Training Epoch: 27 [6912/9756]	Loss: 0.1427	LR: 0.004000
Training Epoch: 27 [7168/9756]	Loss: 0.1276	LR: 0.004000
Training Epoch: 27 [7424/9756]	Loss: 0.1741	LR: 0.004000
Training Epoch: 27 [7680/9756]	Loss: 0.1195	LR: 0.004000
Training Epoch: 27 [7936/9756]	Loss: 0.1568	LR: 0.004000
Training Epoch: 27 [8192/9756]	Loss: 0.1054	LR: 0.004000
Training Epoch: 27 [8448/9756]	Loss: 0.1205	LR: 0.004000
Training Epoch: 27 [8704/9756]	Loss: 0.1338	LR: 0.004000
Training Epoch: 27 [8960/9756]	Loss: 0.1462	LR: 0.004000
Training Epoch: 27 [9216/9756]	Loss: 0.1328	LR: 0.004000
Training Epoch: 27 [9472/9756]	Loss: 0.1419	LR: 0.004000
Training Epoch: 27 [9728/9756]	Loss: 0.2058	LR: 0.004000
Training Epoch: 27 [9756/9756]	Loss: 0.1008	LR: 0.004000
Epoch 27 - Average Train Loss: 0.1408, Train Accuracy: 0.9407
Epoch 27 training time consumed: 140.40s
Evaluating Network.....
Test set: Epoch: 27, Average loss: 0.0006, Accuracy: 0.9419, Time consumed:7.98s
Training Epoch: 28 [256/9756]	Loss: 0.1666	LR: 0.004000
Training Epoch: 28 [512/9756]	Loss: 0.1486	LR: 0.004000
Training Epoch: 28 [768/9756]	Loss: 0.1565	LR: 0.004000
Training Epoch: 28 [1024/9756]	Loss: 0.1477	LR: 0.004000
Training Epoch: 28 [1280/9756]	Loss: 0.1799	LR: 0.004000
Training Epoch: 28 [1536/9756]	Loss: 0.1679	LR: 0.004000
Training Epoch: 28 [1792/9756]	Loss: 0.2173	LR: 0.004000
Training Epoch: 28 [2048/9756]	Loss: 0.1220	LR: 0.004000
Training Epoch: 28 [2304/9756]	Loss: 0.1135	LR: 0.004000
Training Epoch: 28 [2560/9756]	Loss: 0.1642	LR: 0.004000
Training Epoch: 28 [2816/9756]	Loss: 0.1367	LR: 0.004000
Training Epoch: 28 [3072/9756]	Loss: 0.1482	LR: 0.004000
Training Epoch: 28 [3328/9756]	Loss: 0.1613	LR: 0.004000
Training Epoch: 28 [3584/9756]	Loss: 0.1269	LR: 0.004000
Training Epoch: 28 [3840/9756]	Loss: 0.1598	LR: 0.004000
Training Epoch: 28 [4096/9756]	Loss: 0.1733	LR: 0.004000
Training Epoch: 28 [4352/9756]	Loss: 0.1573	LR: 0.004000
Training Epoch: 28 [4608/9756]	Loss: 0.1153	LR: 0.004000
Training Epoch: 28 [4864/9756]	Loss: 0.1137	LR: 0.004000
Training Epoch: 28 [5120/9756]	Loss: 0.1146	LR: 0.004000
Training Epoch: 28 [5376/9756]	Loss: 0.1080	LR: 0.004000
Training Epoch: 28 [5632/9756]	Loss: 0.1199	LR: 0.004000
Training Epoch: 28 [5888/9756]	Loss: 0.1221	LR: 0.004000
Training Epoch: 28 [6144/9756]	Loss: 0.1169	LR: 0.004000
Training Epoch: 28 [6400/9756]	Loss: 0.1226	LR: 0.004000
Training Epoch: 28 [6656/9756]	Loss: 0.1232	LR: 0.004000
Training Epoch: 28 [6912/9756]	Loss: 0.1176	LR: 0.004000
Training Epoch: 28 [7168/9756]	Loss: 0.1635	LR: 0.004000
Training Epoch: 28 [7424/9756]	Loss: 0.1019	LR: 0.004000
Training Epoch: 28 [7680/9756]	Loss: 0.0915	LR: 0.004000
Training Epoch: 28 [7936/9756]	Loss: 0.0935	LR: 0.004000
Training Epoch: 28 [8192/9756]	Loss: 0.1317	LR: 0.004000
Training Epoch: 28 [8448/9756]	Loss: 0.1397	LR: 0.004000
Training Epoch: 28 [8704/9756]	Loss: 0.1587	LR: 0.004000
Training Epoch: 28 [8960/9756]	Loss: 0.1028	LR: 0.004000
Training Epoch: 28 [9216/9756]	Loss: 0.1412	LR: 0.004000
Training Epoch: 28 [9472/9756]	Loss: 0.1383	LR: 0.004000
Training Epoch: 28 [9728/9756]	Loss: 0.1177	LR: 0.004000
Training Epoch: 28 [9756/9756]	Loss: 0.3922	LR: 0.004000
Epoch 28 - Average Train Loss: 0.1376, Train Accuracy: 0.9434
Epoch 28 training time consumed: 140.20s
Evaluating Network.....
Test set: Epoch: 28, Average loss: 0.0006, Accuracy: 0.9419, Time consumed:8.03s
Training Epoch: 29 [256/9756]	Loss: 0.1620	LR: 0.004000
Training Epoch: 29 [512/9756]	Loss: 0.1272	LR: 0.004000
Training Epoch: 29 [768/9756]	Loss: 0.1356	LR: 0.004000
Training Epoch: 29 [1024/9756]	Loss: 0.1090	LR: 0.004000
Training Epoch: 29 [1280/9756]	Loss: 0.1161	LR: 0.004000
Training Epoch: 29 [1536/9756]	Loss: 0.1421	LR: 0.004000
Training Epoch: 29 [1792/9756]	Loss: 0.1156	LR: 0.004000
Training Epoch: 29 [2048/9756]	Loss: 0.1337	LR: 0.004000
Training Epoch: 29 [2304/9756]	Loss: 0.1960	LR: 0.004000
Training Epoch: 29 [2560/9756]	Loss: 0.1271	LR: 0.004000
Training Epoch: 29 [2816/9756]	Loss: 0.1084	LR: 0.004000
Training Epoch: 29 [3072/9756]	Loss: 0.1097	LR: 0.004000
Training Epoch: 29 [3328/9756]	Loss: 0.1543	LR: 0.004000
Training Epoch: 29 [3584/9756]	Loss: 0.1081	LR: 0.004000
Training Epoch: 29 [3840/9756]	Loss: 0.1297	LR: 0.004000
Training Epoch: 29 [4096/9756]	Loss: 0.1468	LR: 0.004000
Training Epoch: 29 [4352/9756]	Loss: 0.1214	LR: 0.004000
Training Epoch: 29 [4608/9756]	Loss: 0.1254	LR: 0.004000
Training Epoch: 29 [4864/9756]	Loss: 0.1159	LR: 0.004000
Training Epoch: 29 [5120/9756]	Loss: 0.0986	LR: 0.004000
Training Epoch: 29 [5376/9756]	Loss: 0.0954	LR: 0.004000
Training Epoch: 29 [5632/9756]	Loss: 0.1634	LR: 0.004000
Training Epoch: 29 [5888/9756]	Loss: 0.1521	LR: 0.004000
Training Epoch: 29 [6144/9756]	Loss: 0.1596	LR: 0.004000
Training Epoch: 29 [6400/9756]	Loss: 0.1699	LR: 0.004000
Training Epoch: 29 [6656/9756]	Loss: 0.1543	LR: 0.004000
Training Epoch: 29 [6912/9756]	Loss: 0.1010	LR: 0.004000
Training Epoch: 29 [7168/9756]	Loss: 0.1528	LR: 0.004000
Training Epoch: 29 [7424/9756]	Loss: 0.1191	LR: 0.004000
Training Epoch: 29 [7680/9756]	Loss: 0.1118	LR: 0.004000
Training Epoch: 29 [7936/9756]	Loss: 0.1948	LR: 0.004000
Training Epoch: 29 [8192/9756]	Loss: 0.1630	LR: 0.004000
Training Epoch: 29 [8448/9756]	Loss: 0.1518	LR: 0.004000
Training Epoch: 29 [8704/9756]	Loss: 0.2253	LR: 0.004000
Training Epoch: 29 [8960/9756]	Loss: 0.1944	LR: 0.004000
Training Epoch: 29 [9216/9756]	Loss: 0.2216	LR: 0.004000
Training Epoch: 29 [9472/9756]	Loss: 0.1198	LR: 0.004000
Training Epoch: 29 [9728/9756]	Loss: 0.1703	LR: 0.004000
Training Epoch: 29 [9756/9756]	Loss: 0.3121	LR: 0.004000
Epoch 29 - Average Train Loss: 0.1427, Train Accuracy: 0.9415
Epoch 29 training time consumed: 140.79s
Evaluating Network.....
Test set: Epoch: 29, Average loss: 0.0008, Accuracy: 0.9298, Time consumed:8.08s
Training Epoch: 30 [256/9756]	Loss: 0.1811	LR: 0.004000
Training Epoch: 30 [512/9756]	Loss: 0.1218	LR: 0.004000
Training Epoch: 30 [768/9756]	Loss: 0.1404	LR: 0.004000
Training Epoch: 30 [1024/9756]	Loss: 0.1241	LR: 0.004000
Training Epoch: 30 [1280/9756]	Loss: 0.1242	LR: 0.004000
Training Epoch: 30 [1536/9756]	Loss: 0.1425	LR: 0.004000
Training Epoch: 30 [1792/9756]	Loss: 0.2136	LR: 0.004000
Training Epoch: 30 [2048/9756]	Loss: 0.1745	LR: 0.004000
Training Epoch: 30 [2304/9756]	Loss: 0.1173	LR: 0.004000
Training Epoch: 30 [2560/9756]	Loss: 0.1767	LR: 0.004000
Training Epoch: 30 [2816/9756]	Loss: 0.1482	LR: 0.004000
Training Epoch: 30 [3072/9756]	Loss: 0.1046	LR: 0.004000
Training Epoch: 30 [3328/9756]	Loss: 0.0913	LR: 0.004000
Training Epoch: 30 [3584/9756]	Loss: 0.1544	LR: 0.004000
Training Epoch: 30 [3840/9756]	Loss: 0.1657	LR: 0.004000
Training Epoch: 30 [4096/9756]	Loss: 0.1193	LR: 0.004000
Training Epoch: 30 [4352/9756]	Loss: 0.1166	LR: 0.004000
Training Epoch: 30 [4608/9756]	Loss: 0.0917	LR: 0.004000
Training Epoch: 30 [4864/9756]	Loss: 0.1319	LR: 0.004000
Training Epoch: 30 [5120/9756]	Loss: 0.1707	LR: 0.004000
Training Epoch: 30 [5376/9756]	Loss: 0.1693	LR: 0.004000
Training Epoch: 30 [5632/9756]	Loss: 0.1261	LR: 0.004000
Training Epoch: 30 [5888/9756]	Loss: 0.1832	LR: 0.004000
Training Epoch: 30 [6144/9756]	Loss: 0.1265	LR: 0.004000
Training Epoch: 30 [6400/9756]	Loss: 0.1397	LR: 0.004000
Training Epoch: 30 [6656/9756]	Loss: 0.1611	LR: 0.004000
Training Epoch: 30 [6912/9756]	Loss: 0.1351	LR: 0.004000
Training Epoch: 30 [7168/9756]	Loss: 0.1333	LR: 0.004000
Training Epoch: 30 [7424/9756]	Loss: 0.1407	LR: 0.004000
Training Epoch: 30 [7680/9756]	Loss: 0.1170	LR: 0.004000
Training Epoch: 30 [7936/9756]	Loss: 0.1509	LR: 0.004000
Training Epoch: 30 [8192/9756]	Loss: 0.1776	LR: 0.004000
Training Epoch: 30 [8448/9756]	Loss: 0.1180	LR: 0.004000
Training Epoch: 30 [8704/9756]	Loss: 0.1434	LR: 0.004000
Training Epoch: 30 [8960/9756]	Loss: 0.1390	LR: 0.004000
Training Epoch: 30 [9216/9756]	Loss: 0.0944	LR: 0.004000
Training Epoch: 30 [9472/9756]	Loss: 0.1179	LR: 0.004000
Training Epoch: 30 [9728/9756]	Loss: 0.1306	LR: 0.004000
Training Epoch: 30 [9756/9756]	Loss: 0.0609	LR: 0.004000
Epoch 30 - Average Train Loss: 0.1396, Train Accuracy: 0.9435
Epoch 30 training time consumed: 140.81s
Evaluating Network.....
Test set: Epoch: 30, Average loss: 0.0006, Accuracy: 0.9400, Time consumed:7.98s
Training Epoch: 31 [256/9756]	Loss: 0.1128	LR: 0.004000
Training Epoch: 31 [512/9756]	Loss: 0.1577	LR: 0.004000
Training Epoch: 31 [768/9756]	Loss: 0.1326	LR: 0.004000
Training Epoch: 31 [1024/9756]	Loss: 0.1437	LR: 0.004000
Training Epoch: 31 [1280/9756]	Loss: 0.1541	LR: 0.004000
Training Epoch: 31 [1536/9756]	Loss: 0.1174	LR: 0.004000
Training Epoch: 31 [1792/9756]	Loss: 0.1552	LR: 0.004000
Training Epoch: 31 [2048/9756]	Loss: 0.1387	LR: 0.004000
Training Epoch: 31 [2304/9756]	Loss: 0.0962	LR: 0.004000
Training Epoch: 31 [2560/9756]	Loss: 0.1491	LR: 0.004000
Training Epoch: 31 [2816/9756]	Loss: 0.1444	LR: 0.004000
Training Epoch: 31 [3072/9756]	Loss: 0.1042	LR: 0.004000
Training Epoch: 31 [3328/9756]	Loss: 0.1237	LR: 0.004000
Training Epoch: 31 [3584/9756]	Loss: 0.1486	LR: 0.004000
Training Epoch: 31 [3840/9756]	Loss: 0.1123	LR: 0.004000
Training Epoch: 31 [4096/9756]	Loss: 0.1576	LR: 0.004000
Training Epoch: 31 [4352/9756]	Loss: 0.1210	LR: 0.004000
Training Epoch: 31 [4608/9756]	Loss: 0.0838	LR: 0.004000
Training Epoch: 31 [4864/9756]	Loss: 0.1968	LR: 0.004000
Training Epoch: 31 [5120/9756]	Loss: 0.1073	LR: 0.004000
Training Epoch: 31 [5376/9756]	Loss: 0.1507	LR: 0.004000
Training Epoch: 31 [5632/9756]	Loss: 0.1220	LR: 0.004000
Training Epoch: 31 [5888/9756]	Loss: 0.1138	LR: 0.004000
Training Epoch: 31 [6144/9756]	Loss: 0.1498	LR: 0.004000
Training Epoch: 31 [6400/9756]	Loss: 0.1761	LR: 0.004000
Training Epoch: 31 [6656/9756]	Loss: 0.1659	LR: 0.004000
Training Epoch: 31 [6912/9756]	Loss: 0.1910	LR: 0.004000
Training Epoch: 31 [7168/9756]	Loss: 0.1425	LR: 0.004000
Training Epoch: 31 [7424/9756]	Loss: 0.1082	LR: 0.004000
Training Epoch: 31 [7680/9756]	Loss: 0.1194	LR: 0.004000
Training Epoch: 31 [7936/9756]	Loss: 0.1316	LR: 0.004000
Training Epoch: 31 [8192/9756]	Loss: 0.1550	LR: 0.004000
Training Epoch: 31 [8448/9756]	Loss: 0.1208	LR: 0.004000
Training Epoch: 31 [8704/9756]	Loss: 0.1561	LR: 0.004000
Training Epoch: 31 [8960/9756]	Loss: 0.1528	LR: 0.004000
Training Epoch: 31 [9216/9756]	Loss: 0.1648	LR: 0.004000
Training Epoch: 31 [9472/9756]	Loss: 0.1985	LR: 0.004000
Training Epoch: 31 [9728/9756]	Loss: 0.1525	LR: 0.004000
Training Epoch: 31 [9756/9756]	Loss: 0.2345	LR: 0.004000
Epoch 31 - Average Train Loss: 0.1405, Train Accuracy: 0.9407
Epoch 31 training time consumed: 140.19s
Evaluating Network.....
Test set: Epoch: 31, Average loss: 0.0006, Accuracy: 0.9443, Time consumed:7.89s
Saving weights file to checkpoint/retrain/ResNet18/Saturday_26_July_2025_01h_54m_23s/ResNet18-MUCAC-seed4-ret25-31-best.pth
Valid (Test) Dl:  2065
Train Dl:  10548
Retain Train Dl:  9756
Forget Train Dl:  792
Retain Valid Dl:  9756
Forget Valid Dl:  792
retain_prob Distribution: 2065 samples
test_prob Distribution: 2065 samples
forget_prob Distribution: 792 samples
Set1 Distribution: 792 samples
Set2 Distribution: 792 samples
Set1 Distribution: 792 samples
Set2 Distribution: 792 samples
Set1 Distribution: 2065 samples
Set2 Distribution: 2065 samples
Set1 Distribution: 2065 samples
Set2 Distribution: 2065 samples
Test Accuracy: 94.39849090576172
Retain Accuracy: 94.73014068603516
Zero-Retain Forget (ZRF): 0.7057075500488281
Membership Inference Attack (MIA): 0.3345959595959596
Forget vs Retain Membership Inference Attack (MIA): 0.5615141955835962
Forget vs Test Membership Inference Attack (MIA): 0.5457413249211357
Test vs Retain Membership Inference Attack (MIA): 0.5096852300242131
Train vs Test Membership Inference Attack (MIA): 0.5387409200968523
Forget Set Accuracy (Df): 91.30859375
Method Execution Time: 5778.96 seconds
