Hugging Face's logo

guaishou1
/
Met2Net

Model card Files
xet
Community
guaishou1 commited on
Commit
67016f4
·
1 Parent(s): bbc1e88

Add Model

Browse files
Files changed (9) hide show
  1. era5/checkpoints/best-epoch=190-val_loss=0.000.ckpt +3 -0
  2. era5/checkpoints/best.ckpt +3 -0
  3. era5/checkpoints/last.ckpt +3 -0
  4. era5/model_param.json +1 -0
  5. era5/saved/metrics.npy +3 -0
  6. era5/saved/metrics_output.csv +53 -0
  7. era5/saved/preds.npy +3 -0
  8. era5/saved/trues.npy +3 -0
  9. era5/test_20250304_102626.log +1199 -0
era5/checkpoints/best-epoch=190-val_loss=0.000.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38d13e437415b9565e7c154d05fd86e0e848a5489e15711cde96c9b2fabcca55
3
+ size 143304749
era5/checkpoints/best.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38d13e437415b9565e7c154d05fd86e0e848a5489e15711cde96c9b2fabcca55
3
+ size 143304749
era5/checkpoints/last.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9619b2c76b50454954aab03becbebcc5edc85b0de41e2d0dca66647c23b4f49b
3
+ size 143304749
era5/model_param.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"device": "cuda", "dist": false, "res_dir": "work_dirs", "ex_name": "era5/windDir/ITS/w1_0.01_0_lr1e-3_m0.9", "fp16": false, "torchscript": false, "seed": 42, "fps": false, "test": true, "deterministic": false, "batch_size": 4, "val_batch_size": 4, "num_workers": 4, "data_root": "/home/gc/projects/openstl_wind/data", "dataname": "era5wind", "pre_seq_length": 12, "aft_seq_length": 12, "total_length": 24, "use_augment": false, "use_prefetcher": false, "drop_last": false, "method": "its", "config_file": "configs/weather/era5wind/its.py", "model_type": "TAU", "drop": 0.0, "drop_path": 0.1, "overwrite": false, "epoch": 200, "log_step": 1, "opt": "adam", "opt_eps": null, "opt_betas": null, "momentum": 0.9, "weight_decay": 0.0, "clip_grad": null, "clip_mode": "norm", "no_display_method_info": false, "sched": "cosine", "lr": 0.001, "lr_k_decay": 1.0, "warmup_lr": 1e-05, "min_lr": 1e-06, "final_div_factor": 10000.0, "warmup_epoch": 0, "decay_epoch": 100, "decay_rate": 0.1, "filter_bias_and_bn": false, "gpus": [0], "metric_for_bestckpt": "val_loss", "ckpt_path": null, "spatio_kernel_enc": 3, "spatio_kernel_dec": 3, "hid_S": 32, "hid_T": 256, "N_T": 8, "N_S": 4, "momentum_ema": 0.9, "in_shape": [12, 4, 128, 128], "data_name": "era5wind", "metrics": ["mse", "mae", "rmse", "ssim", "psnr"]}
era5/saved/metrics.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65ed57aad196d1b6a9f447cdade47e0f010268458a511c8eab594cc03e6453dd
3
+ size 136
era5/saved/metrics_output.csv ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Lead Time,Channel,MSE,MAE,RMSE,PCC,R²,ACC
2
+ 1,msl,1442.148131,29.175149,37.975625,0.998678,0.997217,0.997215
3
+ 2,msl,2615.517290,39.701802,51.142128,0.997540,0.994947,0.994763
4
+ 3,msl,3889.718827,48.382841,62.367610,0.996342,0.992476,0.992211
5
+ 4,msl,4981.078251,54.435103,70.576754,0.995226,0.990353,0.989842
6
+ 5,msl,6281.894377,61.073990,79.258403,0.993946,0.987816,0.987125
7
+ 6,msl,7709.583609,67.370114,87.804235,0.992567,0.985026,0.984207
8
+ 7,msl,9446.302955,74.596660,97.192093,0.991009,0.981629,0.980916
9
+ 8,msl,11040.681707,79.954242,105.074648,0.989338,0.978500,0.977394
10
+ 9,msl,13221.426454,87.103423,114.984462,0.987253,0.974221,0.973020
11
+ 10,msl,15537.051573,93.676343,124.647710,0.984928,0.969673,0.968143
12
+ 11,msl,18296.284749,101.183217,135.263760,0.982300,0.964250,0.962545
13
+ 12,msl,21281.615675,108.117968,145.882198,0.979164,0.958370,0.955852
14
+ Average,msl,9645.275300,70.397571,92.680802,0.990691,0.981207,0.980269
15
+ 1,u10,0.177354,0.292132,0.421134,0.996911,0.993809,0.990656
16
+ 2,u10,0.357740,0.429781,0.598114,0.993747,0.987507,0.980666
17
+ 3,u10,0.536005,0.533920,0.732124,0.990603,0.981270,0.970826
18
+ 4,u10,0.702913,0.613783,0.838399,0.987639,0.975424,0.961636
19
+ 5,u10,0.870879,0.682147,0.933209,0.984654,0.969536,0.952480
20
+ 6,u10,1.050732,0.747053,1.025052,0.981450,0.963228,0.942650
21
+ 7,u10,1.244240,0.809804,1.115455,0.977996,0.956439,0.932103
22
+ 8,u10,1.452266,0.870707,1.205100,0.974286,0.949141,0.920740
23
+ 9,u10,1.670886,0.928233,1.292628,0.970362,0.941474,0.908699
24
+ 10,u10,1.899357,0.983398,1.378171,0.966249,0.933463,0.896081
25
+ 11,u10,2.136525,1.037855,1.461686,0.961959,0.925147,0.882812
26
+ 12,u10,2.385106,1.092990,1.544379,0.957418,0.916444,0.868528
27
+ Average,u10,1.207000,0.751817,1.045454,0.978606,0.957740,0.933990
28
+ 1,v10,0.176968,0.297836,0.420675,0.995590,0.991071,0.994622
29
+ 2,v10,0.374926,0.448414,0.612312,0.990556,0.981096,0.988263
30
+ 3,v10,0.584398,0.566483,0.764459,0.985218,0.970552,0.981590
31
+ 4,v10,0.784101,0.657087,0.885495,0.980104,0.960514,0.975295
32
+ 5,v10,0.984300,0.734490,0.992119,0.974956,0.950466,0.969045
33
+ 6,v10,1.185604,0.803405,1.088854,0.969764,0.940383,0.962835
34
+ 7,v10,1.389666,0.865798,1.178841,0.964488,0.930183,0.956550
35
+ 8,v10,1.601347,0.924557,1.265443,0.958994,0.919620,0.950029
36
+ 9,v10,1.819691,0.981036,1.348959,0.953336,0.908739,0.943313
37
+ 10,v10,2.044595,1.034591,1.429893,0.947493,0.897543,0.936369
38
+ 11,v10,2.280895,1.088417,1.510263,0.941317,0.885787,0.929011
39
+ 12,v10,2.522717,1.143212,1.588306,0.934971,0.873777,0.921383
40
+ Average,v10,1.312434,0.795444,1.090468,0.966399,0.934144,0.959025
41
+ 1,t2m,0.244150,0.321986,0.494116,0.999247,0.998487,0.991533
42
+ 2,t2m,0.360720,0.390176,0.600600,0.998886,0.997765,0.987230
43
+ 3,t2m,0.479661,0.452766,0.692575,0.998519,0.997027,0.983011
44
+ 4,t2m,0.600509,0.506825,0.774925,0.998146,0.996278,0.978720
45
+ 5,t2m,0.689196,0.548265,0.830179,0.997879,0.995727,0.975627
46
+ 6,t2m,0.791509,0.591231,0.889668,0.997561,0.995091,0.971946
47
+ 7,t2m,0.876941,0.625434,0.936451,0.997299,0.994558,0.968979
48
+ 8,t2m,0.980430,0.661723,0.990166,0.996996,0.993913,0.965587
49
+ 9,t2m,1.065290,0.691728,1.032129,0.996725,0.993383,0.962369
50
+ 10,t2m,1.146021,0.720471,1.070524,0.996489,0.992877,0.959707
51
+ 11,t2m,1.242505,0.750614,1.114677,0.996196,0.992272,0.956298
52
+ 12,t2m,1.333822,0.778527,1.154912,0.995911,0.991699,0.952770
53
+ Average,t2m,0.817563,0.586645,0.881743,0.997488,0.994923,0.971148
era5/saved/preds.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eab3268fb38a85041c7c9aeb6e03de5daabc88cd1811b45ee86b9326e32916a
3
+ size 2293235840
era5/saved/trues.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbf37dc786271f11a6b873866a70ed9bbbb3a659564f525a73c9c6c8821682ce
3
+ size 2293235840
era5/test_20250304_102626.log ADDED
@@ -0,0 +1,1199 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2025-03-04 10:26:27,752 - Environment info:
2
+ ------------------------------------------------------------
3
+ sys.platform: linux
4
+ Python: 3.10.8 | packaged by conda-forge | (main, Nov 22 2022, 08:26:04) [GCC 10.4.0]
5
+ CUDA available: True
6
+ CUDA_HOME: None
7
+ GPU 0: NVIDIA GeForce RTX 4090
8
+ GCC: gcc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
9
+ PyTorch: 2.3.0
10
+ PyTorch compiling details: PyTorch built with:
11
+ - GCC 9.3
12
+ - C++ Version: 201703
13
+ - Intel(R) oneAPI Math Kernel Library Version 2022.1-Product Build 20220311 for Intel(R) 64 architecture applications
14
+ - Intel(R) MKL-DNN v3.3.6 (Git Hash 86e6af5974177e513fd3fee58425e1063e7f1361)
15
+ - OpenMP 201511 (a.k.a. OpenMP 4.5)
16
+ - LAPACK is enabled (usually provided by MKL)
17
+ - NNPACK is enabled
18
+ - CPU capability usage: AVX512
19
+ - CUDA Runtime 12.1
20
+ - NVCC architecture flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_90,code=sm_90
21
+ - CuDNN 8.9.2
22
+ - Magma 2.6.1
23
+ - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=12.1, CUDNN_VERSION=8.9.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=pedantic -Wno-error=old-style-cast -Wno-missing-braces -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=2.3.0, USE_CUDA=ON, USE_CUDNN=ON, USE_CUSPARSELT=1, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF,
24
+
25
+ TorchVision: 0.18.0
26
+ OpenCV: 4.10.0
27
+ openstl: 1.0.0
28
+ ------------------------------------------------------------
29
+
30
+ 2025-03-04 10:26:27,753 -
31
+ device: cuda
32
+ dist: False
33
+ res_dir: work_dirs
34
+ ex_name: era5/windDir/ITS/w1_0.01_0_lr1e-3_m0.9
35
+ fp16: False
36
+ torchscript: False
37
+ seed: 42
38
+ fps: False
39
+ test: True
40
+ deterministic: False
41
+ batch_size: 4
42
+ val_batch_size: 4
43
+ num_workers: 4
44
+ data_root: /home/gc/projects/openstl_wind/data
45
+ dataname: era5wind
46
+ pre_seq_length: 12
47
+ aft_seq_length: 12
48
+ total_length: 24
49
+ use_augment: False
50
+ use_prefetcher: False
51
+ drop_last: False
52
+ method: its
53
+ config_file: configs/weather/era5wind/its.py
54
+ model_type: TAU
55
+ drop: 0.0
56
+ drop_path: 0.1
57
+ overwrite: False
58
+ epoch: 200
59
+ log_step: 1
60
+ opt: adam
61
+ opt_eps: None
62
+ opt_betas: None
63
+ momentum: 0.9
64
+ weight_decay: 0.0
65
+ clip_grad: None
66
+ clip_mode: norm
67
+ no_display_method_info: False
68
+ sched: cosine
69
+ lr: 0.001
70
+ lr_k_decay: 1.0
71
+ warmup_lr: 1e-05
72
+ min_lr: 1e-06
73
+ final_div_factor: 10000.0
74
+ warmup_epoch: 0
75
+ decay_epoch: 100
76
+ decay_rate: 0.1
77
+ filter_bias_and_bn: False
78
+ gpus: [0]
79
+ metric_for_bestckpt: val_loss
80
+ ckpt_path: None
81
+ spatio_kernel_enc: 3
82
+ spatio_kernel_dec: 3
83
+ hid_S: 32
84
+ hid_T: 256
85
+ N_T: 8
86
+ N_S: 4
87
+ momentum_ema: 0.9
88
+ in_shape: [12, 4, 128, 128]
89
+ data_name: era5wind
90
+ metrics: ['mse', 'mae', 'rmse', 'ssim', 'psnr']
91
+ 2025-03-04 10:26:27,754 - Model info:
92
+ SimVP_Model(
93
+ (enc_u10_q): Encoder(
94
+ (enc): Sequential(
95
+ (0): ConvSC(
96
+ (conv): BasicConv2d(
97
+ (conv): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
98
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
99
+ (act): SiLU()
100
+ )
101
+ )
102
+ (1): ConvSC(
103
+ (conv): BasicConv2d(
104
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
105
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
106
+ (act): SiLU()
107
+ )
108
+ )
109
+ (2): ConvSC(
110
+ (conv): BasicConv2d(
111
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
112
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
113
+ (act): SiLU()
114
+ )
115
+ )
116
+ (3): ConvSC(
117
+ (conv): BasicConv2d(
118
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
119
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
120
+ (act): SiLU()
121
+ )
122
+ )
123
+ )
124
+ )
125
+ (enc_u10_k): Encoder(
126
+ (enc): Sequential(
127
+ (0): ConvSC(
128
+ (conv): BasicConv2d(
129
+ (conv): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
130
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
131
+ (act): SiLU()
132
+ )
133
+ )
134
+ (1): ConvSC(
135
+ (conv): BasicConv2d(
136
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
137
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
138
+ (act): SiLU()
139
+ )
140
+ )
141
+ (2): ConvSC(
142
+ (conv): BasicConv2d(
143
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
144
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
145
+ (act): SiLU()
146
+ )
147
+ )
148
+ (3): ConvSC(
149
+ (conv): BasicConv2d(
150
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
151
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
152
+ (act): SiLU()
153
+ )
154
+ )
155
+ )
156
+ )
157
+ (enc_v10_q): Encoder(
158
+ (enc): Sequential(
159
+ (0): ConvSC(
160
+ (conv): BasicConv2d(
161
+ (conv): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
162
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
163
+ (act): SiLU()
164
+ )
165
+ )
166
+ (1): ConvSC(
167
+ (conv): BasicConv2d(
168
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
169
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
170
+ (act): SiLU()
171
+ )
172
+ )
173
+ (2): ConvSC(
174
+ (conv): BasicConv2d(
175
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
176
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
177
+ (act): SiLU()
178
+ )
179
+ )
180
+ (3): ConvSC(
181
+ (conv): BasicConv2d(
182
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
183
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
184
+ (act): SiLU()
185
+ )
186
+ )
187
+ )
188
+ )
189
+ (enc_v10_k): Encoder(
190
+ (enc): Sequential(
191
+ (0): ConvSC(
192
+ (conv): BasicConv2d(
193
+ (conv): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
194
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
195
+ (act): SiLU()
196
+ )
197
+ )
198
+ (1): ConvSC(
199
+ (conv): BasicConv2d(
200
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
201
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
202
+ (act): SiLU()
203
+ )
204
+ )
205
+ (2): ConvSC(
206
+ (conv): BasicConv2d(
207
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
208
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
209
+ (act): SiLU()
210
+ )
211
+ )
212
+ (3): ConvSC(
213
+ (conv): BasicConv2d(
214
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
215
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
216
+ (act): SiLU()
217
+ )
218
+ )
219
+ )
220
+ )
221
+ (enc_tem_q): Encoder(
222
+ (enc): Sequential(
223
+ (0): ConvSC(
224
+ (conv): BasicConv2d(
225
+ (conv): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
226
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
227
+ (act): SiLU()
228
+ )
229
+ )
230
+ (1): ConvSC(
231
+ (conv): BasicConv2d(
232
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
233
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
234
+ (act): SiLU()
235
+ )
236
+ )
237
+ (2): ConvSC(
238
+ (conv): BasicConv2d(
239
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
240
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
241
+ (act): SiLU()
242
+ )
243
+ )
244
+ (3): ConvSC(
245
+ (conv): BasicConv2d(
246
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
247
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
248
+ (act): SiLU()
249
+ )
250
+ )
251
+ )
252
+ )
253
+ (enc_tem_k): Encoder(
254
+ (enc): Sequential(
255
+ (0): ConvSC(
256
+ (conv): BasicConv2d(
257
+ (conv): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
258
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
259
+ (act): SiLU()
260
+ )
261
+ )
262
+ (1): ConvSC(
263
+ (conv): BasicConv2d(
264
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
265
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
266
+ (act): SiLU()
267
+ )
268
+ )
269
+ (2): ConvSC(
270
+ (conv): BasicConv2d(
271
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
272
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
273
+ (act): SiLU()
274
+ )
275
+ )
276
+ (3): ConvSC(
277
+ (conv): BasicConv2d(
278
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
279
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
280
+ (act): SiLU()
281
+ )
282
+ )
283
+ )
284
+ )
285
+ (enc_wind_q): Encoder(
286
+ (enc): Sequential(
287
+ (0): ConvSC(
288
+ (conv): BasicConv2d(
289
+ (conv): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
290
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
291
+ (act): SiLU()
292
+ )
293
+ )
294
+ (1): ConvSC(
295
+ (conv): BasicConv2d(
296
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
297
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
298
+ (act): SiLU()
299
+ )
300
+ )
301
+ (2): ConvSC(
302
+ (conv): BasicConv2d(
303
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
304
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
305
+ (act): SiLU()
306
+ )
307
+ )
308
+ (3): ConvSC(
309
+ (conv): BasicConv2d(
310
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
311
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
312
+ (act): SiLU()
313
+ )
314
+ )
315
+ )
316
+ )
317
+ (enc_wind_k): Encoder(
318
+ (enc): Sequential(
319
+ (0): ConvSC(
320
+ (conv): BasicConv2d(
321
+ (conv): Conv2d(1, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
322
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
323
+ (act): SiLU()
324
+ )
325
+ )
326
+ (1): ConvSC(
327
+ (conv): BasicConv2d(
328
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
329
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
330
+ (act): SiLU()
331
+ )
332
+ )
333
+ (2): ConvSC(
334
+ (conv): BasicConv2d(
335
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
336
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
337
+ (act): SiLU()
338
+ )
339
+ )
340
+ (3): ConvSC(
341
+ (conv): BasicConv2d(
342
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
343
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
344
+ (act): SiLU()
345
+ )
346
+ )
347
+ )
348
+ )
349
+ (dec_u10_q): Decoder(
350
+ (dec): Sequential(
351
+ (0): ConvSC(
352
+ (conv): BasicConv2d(
353
+ (conv): Sequential(
354
+ (0): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
355
+ (1): PixelShuffle(upscale_factor=2)
356
+ )
357
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
358
+ (act): SiLU()
359
+ )
360
+ )
361
+ (1): ConvSC(
362
+ (conv): BasicConv2d(
363
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
364
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
365
+ (act): SiLU()
366
+ )
367
+ )
368
+ (2): ConvSC(
369
+ (conv): BasicConv2d(
370
+ (conv): Sequential(
371
+ (0): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
372
+ (1): PixelShuffle(upscale_factor=2)
373
+ )
374
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
375
+ (act): SiLU()
376
+ )
377
+ )
378
+ (3): ConvSC(
379
+ (conv): BasicConv2d(
380
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
381
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
382
+ (act): SiLU()
383
+ )
384
+ )
385
+ )
386
+ (readout): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
387
+ )
388
+ (dec_u10_k): Decoder(
389
+ (dec): Sequential(
390
+ (0): ConvSC(
391
+ (conv): BasicConv2d(
392
+ (conv): Sequential(
393
+ (0): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
394
+ (1): PixelShuffle(upscale_factor=2)
395
+ )
396
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
397
+ (act): SiLU()
398
+ )
399
+ )
400
+ (1): ConvSC(
401
+ (conv): BasicConv2d(
402
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
403
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
404
+ (act): SiLU()
405
+ )
406
+ )
407
+ (2): ConvSC(
408
+ (conv): BasicConv2d(
409
+ (conv): Sequential(
410
+ (0): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
411
+ (1): PixelShuffle(upscale_factor=2)
412
+ )
413
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
414
+ (act): SiLU()
415
+ )
416
+ )
417
+ (3): ConvSC(
418
+ (conv): BasicConv2d(
419
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
420
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
421
+ (act): SiLU()
422
+ )
423
+ )
424
+ )
425
+ (readout): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
426
+ )
427
+ (dec_v10_q): Decoder(
428
+ (dec): Sequential(
429
+ (0): ConvSC(
430
+ (conv): BasicConv2d(
431
+ (conv): Sequential(
432
+ (0): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
433
+ (1): PixelShuffle(upscale_factor=2)
434
+ )
435
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
436
+ (act): SiLU()
437
+ )
438
+ )
439
+ (1): ConvSC(
440
+ (conv): BasicConv2d(
441
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
442
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
443
+ (act): SiLU()
444
+ )
445
+ )
446
+ (2): ConvSC(
447
+ (conv): BasicConv2d(
448
+ (conv): Sequential(
449
+ (0): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
450
+ (1): PixelShuffle(upscale_factor=2)
451
+ )
452
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
453
+ (act): SiLU()
454
+ )
455
+ )
456
+ (3): ConvSC(
457
+ (conv): BasicConv2d(
458
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
459
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
460
+ (act): SiLU()
461
+ )
462
+ )
463
+ )
464
+ (readout): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
465
+ )
466
+ (dec_v10_k): Decoder(
467
+ (dec): Sequential(
468
+ (0): ConvSC(
469
+ (conv): BasicConv2d(
470
+ (conv): Sequential(
471
+ (0): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
472
+ (1): PixelShuffle(upscale_factor=2)
473
+ )
474
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
475
+ (act): SiLU()
476
+ )
477
+ )
478
+ (1): ConvSC(
479
+ (conv): BasicConv2d(
480
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
481
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
482
+ (act): SiLU()
483
+ )
484
+ )
485
+ (2): ConvSC(
486
+ (conv): BasicConv2d(
487
+ (conv): Sequential(
488
+ (0): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
489
+ (1): PixelShuffle(upscale_factor=2)
490
+ )
491
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
492
+ (act): SiLU()
493
+ )
494
+ )
495
+ (3): ConvSC(
496
+ (conv): BasicConv2d(
497
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
498
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
499
+ (act): SiLU()
500
+ )
501
+ )
502
+ )
503
+ (readout): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
504
+ )
505
+ (dec_tem_q): Decoder(
506
+ (dec): Sequential(
507
+ (0): ConvSC(
508
+ (conv): BasicConv2d(
509
+ (conv): Sequential(
510
+ (0): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
511
+ (1): PixelShuffle(upscale_factor=2)
512
+ )
513
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
514
+ (act): SiLU()
515
+ )
516
+ )
517
+ (1): ConvSC(
518
+ (conv): BasicConv2d(
519
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
520
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
521
+ (act): SiLU()
522
+ )
523
+ )
524
+ (2): ConvSC(
525
+ (conv): BasicConv2d(
526
+ (conv): Sequential(
527
+ (0): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
528
+ (1): PixelShuffle(upscale_factor=2)
529
+ )
530
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
531
+ (act): SiLU()
532
+ )
533
+ )
534
+ (3): ConvSC(
535
+ (conv): BasicConv2d(
536
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
537
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
538
+ (act): SiLU()
539
+ )
540
+ )
541
+ )
542
+ (readout): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
543
+ )
544
+ (dec_tem_k): Decoder(
545
+ (dec): Sequential(
546
+ (0): ConvSC(
547
+ (conv): BasicConv2d(
548
+ (conv): Sequential(
549
+ (0): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
550
+ (1): PixelShuffle(upscale_factor=2)
551
+ )
552
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
553
+ (act): SiLU()
554
+ )
555
+ )
556
+ (1): ConvSC(
557
+ (conv): BasicConv2d(
558
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
559
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
560
+ (act): SiLU()
561
+ )
562
+ )
563
+ (2): ConvSC(
564
+ (conv): BasicConv2d(
565
+ (conv): Sequential(
566
+ (0): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
567
+ (1): PixelShuffle(upscale_factor=2)
568
+ )
569
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
570
+ (act): SiLU()
571
+ )
572
+ )
573
+ (3): ConvSC(
574
+ (conv): BasicConv2d(
575
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
576
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
577
+ (act): SiLU()
578
+ )
579
+ )
580
+ )
581
+ (readout): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
582
+ )
583
+ (dec_wind_q): Decoder(
584
+ (dec): Sequential(
585
+ (0): ConvSC(
586
+ (conv): BasicConv2d(
587
+ (conv): Sequential(
588
+ (0): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
589
+ (1): PixelShuffle(upscale_factor=2)
590
+ )
591
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
592
+ (act): SiLU()
593
+ )
594
+ )
595
+ (1): ConvSC(
596
+ (conv): BasicConv2d(
597
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
598
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
599
+ (act): SiLU()
600
+ )
601
+ )
602
+ (2): ConvSC(
603
+ (conv): BasicConv2d(
604
+ (conv): Sequential(
605
+ (0): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
606
+ (1): PixelShuffle(upscale_factor=2)
607
+ )
608
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
609
+ (act): SiLU()
610
+ )
611
+ )
612
+ (3): ConvSC(
613
+ (conv): BasicConv2d(
614
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
615
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
616
+ (act): SiLU()
617
+ )
618
+ )
619
+ )
620
+ (readout): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
621
+ )
622
+ (dec_wind_k): Decoder(
623
+ (dec): Sequential(
624
+ (0): ConvSC(
625
+ (conv): BasicConv2d(
626
+ (conv): Sequential(
627
+ (0): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
628
+ (1): PixelShuffle(upscale_factor=2)
629
+ )
630
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
631
+ (act): SiLU()
632
+ )
633
+ )
634
+ (1): ConvSC(
635
+ (conv): BasicConv2d(
636
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
637
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
638
+ (act): SiLU()
639
+ )
640
+ )
641
+ (2): ConvSC(
642
+ (conv): BasicConv2d(
643
+ (conv): Sequential(
644
+ (0): Conv2d(32, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
645
+ (1): PixelShuffle(upscale_factor=2)
646
+ )
647
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
648
+ (act): SiLU()
649
+ )
650
+ )
651
+ (3): ConvSC(
652
+ (conv): BasicConv2d(
653
+ (conv): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
654
+ (norm): GroupNorm(2, 32, eps=1e-05, affine=True)
655
+ (act): SiLU()
656
+ )
657
+ )
658
+ )
659
+ (readout): Conv2d(32, 1, kernel_size=(1, 1), stride=(1, 1))
660
+ )
661
+ (hid_q): CIMidNet(
662
+ (conv1): Conv2d(384, 256, kernel_size=(1, 1), stride=(1, 1))
663
+ (layers): ModuleList(
664
+ (0-7): 8 x CIAttBlock(
665
+ (norm_1): GroupNorm(1, 256, eps=1e-05, affine=True)
666
+ (norm_2): GroupNorm(1, 256, eps=1e-05, affine=True)
667
+ (attn_1): MultiHeadAttention_S(
668
+ (q_Conv): Sequential(
669
+ (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
670
+ (1): GroupNorm(1, 256, eps=1e-05, affine=True)
671
+ )
672
+ (v_Conv): Sequential(
673
+ (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
674
+ (1): GroupNorm(1, 256, eps=1e-05, affine=True)
675
+ )
676
+ (k_Conv): Sequential(
677
+ (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
678
+ (1): GroupNorm(1, 256, eps=1e-05, affine=True)
679
+ )
680
+ (v_post_f): Sequential(
681
+ (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
682
+ (1): GroupNorm(1, 256, eps=1e-05, affine=True)
683
+ (2): SiLU()
684
+ )
685
+ )
686
+ (ff): layerNormFeedForward(
687
+ (ff1): TAUSubBlock(
688
+ (norm1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
689
+ (attn): TemporalAttention(
690
+ (proj_1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
691
+ (activation): GELU(approximate='none')
692
+ (spatial_gating_unit): TemporalAttentionModule(
693
+ (conv0): Conv2d(256, 256, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=256)
694
+ (conv_spatial): Conv2d(256, 256, kernel_size=(7, 7), stride=(1, 1), padding=(9, 9), dilation=(3, 3), groups=256)
695
+ (conv1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
696
+ (avg_pool): AdaptiveAvgPool2d(output_size=1)
697
+ (fc): Sequential(
698
+ (0): Linear(in_features=256, out_features=16, bias=False)
699
+ (1): ReLU(inplace=True)
700
+ (2): Linear(in_features=16, out_features=256, bias=False)
701
+ (3): Sigmoid()
702
+ )
703
+ )
704
+ (proj_2): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
705
+ )
706
+ (drop_path): DropPath(drop_prob=0.100)
707
+ (norm2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
708
+ (mlp): MixMlp(
709
+ (fc1): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1))
710
+ (dwconv): DWConv(
711
+ (dwconv): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=1024)
712
+ )
713
+ (act): GELU(approximate='none')
714
+ (fc2): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1))
715
+ (drop): Dropout(p=0.0, inplace=False)
716
+ )
717
+ )
718
+ )
719
+ )
720
+ )
721
+ (conv2): Conv2d(256, 384, kernel_size=(1, 1), stride=(1, 1))
722
+ )
723
+ (hid_k): CIMidNet(
724
+ (conv1): Conv2d(384, 256, kernel_size=(1, 1), stride=(1, 1))
725
+ (layers): ModuleList(
726
+ (0-7): 8 x CIAttBlock(
727
+ (norm_1): GroupNorm(1, 256, eps=1e-05, affine=True)
728
+ (norm_2): GroupNorm(1, 256, eps=1e-05, affine=True)
729
+ (attn_1): MultiHeadAttention_S(
730
+ (q_Conv): Sequential(
731
+ (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
732
+ (1): GroupNorm(1, 256, eps=1e-05, affine=True)
733
+ )
734
+ (v_Conv): Sequential(
735
+ (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
736
+ (1): GroupNorm(1, 256, eps=1e-05, affine=True)
737
+ )
738
+ (k_Conv): Sequential(
739
+ (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
740
+ (1): GroupNorm(1, 256, eps=1e-05, affine=True)
741
+ )
742
+ (v_post_f): Sequential(
743
+ (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
744
+ (1): GroupNorm(1, 256, eps=1e-05, affine=True)
745
+ (2): SiLU()
746
+ )
747
+ )
748
+ (ff): layerNormFeedForward(
749
+ (ff1): TAUSubBlock(
750
+ (norm1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
751
+ (attn): TemporalAttention(
752
+ (proj_1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
753
+ (activation): GELU(approximate='none')
754
+ (spatial_gating_unit): TemporalAttentionModule(
755
+ (conv0): Conv2d(256, 256, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=256)
756
+ (conv_spatial): Conv2d(256, 256, kernel_size=(7, 7), stride=(1, 1), padding=(9, 9), dilation=(3, 3), groups=256)
757
+ (conv1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
758
+ (avg_pool): AdaptiveAvgPool2d(output_size=1)
759
+ (fc): Sequential(
760
+ (0): Linear(in_features=256, out_features=16, bias=False)
761
+ (1): ReLU(inplace=True)
762
+ (2): Linear(in_features=16, out_features=256, bias=False)
763
+ (3): Sigmoid()
764
+ )
765
+ )
766
+ (proj_2): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1))
767
+ )
768
+ (drop_path): DropPath(drop_prob=0.100)
769
+ (norm2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
770
+ (mlp): MixMlp(
771
+ (fc1): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1))
772
+ (dwconv): DWConv(
773
+ (dwconv): Conv2d(1024, 1024, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=1024)
774
+ )
775
+ (act): GELU(approximate='none')
776
+ (fc2): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1))
777
+ (drop): Dropout(p=0.0, inplace=False)
778
+ )
779
+ )
780
+ )
781
+ )
782
+ )
783
+ (conv2): Conv2d(256, 384, kernel_size=(1, 1), stride=(1, 1))
784
+ )
785
+ )
786
+ | module | #parameters or shape | #flops |
787
+ |:------------------------------|:-----------------------|:-----------|
788
+ | model | 17.805M | 0.119T |
789
+ | enc_u10_q.enc | 28.32K | 1.125G |
790
+ | enc_u10_q.enc.0.conv | 0.384K | 88.08M |
791
+ | enc_u10_q.enc.0.conv.conv | 0.32K | 56.623M |
792
+ | enc_u10_q.enc.0.conv.norm | 64 | 31.457M |
793
+ | enc_u10_q.enc.1.conv | 9.312K | 0.461G |
794
+ | enc_u10_q.enc.1.conv.conv | 9.248K | 0.453G |
795
+ | enc_u10_q.enc.1.conv.norm | 64 | 7.864M |
796
+ | enc_u10_q.enc.2.conv | 9.312K | 0.461G |
797
+ | enc_u10_q.enc.2.conv.conv | 9.248K | 0.453G |
798
+ | enc_u10_q.enc.2.conv.norm | 64 | 7.864M |
799
+ | enc_u10_q.enc.3.conv | 9.312K | 0.115G |
800
+ | enc_u10_q.enc.3.conv.conv | 9.248K | 0.113G |
801
+ | enc_u10_q.enc.3.conv.norm | 64 | 1.966M |
802
+ | enc_u10_k.enc | 28.32K | 2.25G |
803
+ | enc_u10_k.enc.0.conv | 0.384K | 0.176G |
804
+ | enc_u10_k.enc.0.conv.conv | 0.32K | 0.113G |
805
+ | enc_u10_k.enc.0.conv.norm | 64 | 62.915M |
806
+ | enc_u10_k.enc.1.conv | 9.312K | 0.922G |
807
+ | enc_u10_k.enc.1.conv.conv | 9.248K | 0.906G |
808
+ | enc_u10_k.enc.1.conv.norm | 64 | 15.729M |
809
+ | enc_u10_k.enc.2.conv | 9.312K | 0.922G |
810
+ | enc_u10_k.enc.2.conv.conv | 9.248K | 0.906G |
811
+ | enc_u10_k.enc.2.conv.norm | 64 | 15.729M |
812
+ | enc_u10_k.enc.3.conv | 9.312K | 0.23G |
813
+ | enc_u10_k.enc.3.conv.conv | 9.248K | 0.226G |
814
+ | enc_u10_k.enc.3.conv.norm | 64 | 3.932M |
815
+ | enc_v10_q.enc | 28.32K | 1.125G |
816
+ | enc_v10_q.enc.0.conv | 0.384K | 88.08M |
817
+ | enc_v10_q.enc.0.conv.conv | 0.32K | 56.623M |
818
+ | enc_v10_q.enc.0.conv.norm | 64 | 31.457M |
819
+ | enc_v10_q.enc.1.conv | 9.312K | 0.461G |
820
+ | enc_v10_q.enc.1.conv.conv | 9.248K | 0.453G |
821
+ | enc_v10_q.enc.1.conv.norm | 64 | 7.864M |
822
+ | enc_v10_q.enc.2.conv | 9.312K | 0.461G |
823
+ | enc_v10_q.enc.2.conv.conv | 9.248K | 0.453G |
824
+ | enc_v10_q.enc.2.conv.norm | 64 | 7.864M |
825
+ | enc_v10_q.enc.3.conv | 9.312K | 0.115G |
826
+ | enc_v10_q.enc.3.conv.conv | 9.248K | 0.113G |
827
+ | enc_v10_q.enc.3.conv.norm | 64 | 1.966M |
828
+ | enc_v10_k.enc | 28.32K | 2.25G |
829
+ | enc_v10_k.enc.0.conv | 0.384K | 0.176G |
830
+ | enc_v10_k.enc.0.conv.conv | 0.32K | 0.113G |
831
+ | enc_v10_k.enc.0.conv.norm | 64 | 62.915M |
832
+ | enc_v10_k.enc.1.conv | 9.312K | 0.922G |
833
+ | enc_v10_k.enc.1.conv.conv | 9.248K | 0.906G |
834
+ | enc_v10_k.enc.1.conv.norm | 64 | 15.729M |
835
+ | enc_v10_k.enc.2.conv | 9.312K | 0.922G |
836
+ | enc_v10_k.enc.2.conv.conv | 9.248K | 0.906G |
837
+ | enc_v10_k.enc.2.conv.norm | 64 | 15.729M |
838
+ | enc_v10_k.enc.3.conv | 9.312K | 0.23G |
839
+ | enc_v10_k.enc.3.conv.conv | 9.248K | 0.226G |
840
+ | enc_v10_k.enc.3.conv.norm | 64 | 3.932M |
841
+ | enc_tem_q.enc | 28.32K | 1.125G |
842
+ | enc_tem_q.enc.0.conv | 0.384K | 88.08M |
843
+ | enc_tem_q.enc.0.conv.conv | 0.32K | 56.623M |
844
+ | enc_tem_q.enc.0.conv.norm | 64 | 31.457M |
845
+ | enc_tem_q.enc.1.conv | 9.312K | 0.461G |
846
+ | enc_tem_q.enc.1.conv.conv | 9.248K | 0.453G |
847
+ | enc_tem_q.enc.1.conv.norm | 64 | 7.864M |
848
+ | enc_tem_q.enc.2.conv | 9.312K | 0.461G |
849
+ | enc_tem_q.enc.2.conv.conv | 9.248K | 0.453G |
850
+ | enc_tem_q.enc.2.conv.norm | 64 | 7.864M |
851
+ | enc_tem_q.enc.3.conv | 9.312K | 0.115G |
852
+ | enc_tem_q.enc.3.conv.conv | 9.248K | 0.113G |
853
+ | enc_tem_q.enc.3.conv.norm | 64 | 1.966M |
854
+ | enc_tem_k.enc | 28.32K | 2.25G |
855
+ | enc_tem_k.enc.0.conv | 0.384K | 0.176G |
856
+ | enc_tem_k.enc.0.conv.conv | 0.32K | 0.113G |
857
+ | enc_tem_k.enc.0.conv.norm | 64 | 62.915M |
858
+ | enc_tem_k.enc.1.conv | 9.312K | 0.922G |
859
+ | enc_tem_k.enc.1.conv.conv | 9.248K | 0.906G |
860
+ | enc_tem_k.enc.1.conv.norm | 64 | 15.729M |
861
+ | enc_tem_k.enc.2.conv | 9.312K | 0.922G |
862
+ | enc_tem_k.enc.2.conv.conv | 9.248K | 0.906G |
863
+ | enc_tem_k.enc.2.conv.norm | 64 | 15.729M |
864
+ | enc_tem_k.enc.3.conv | 9.312K | 0.23G |
865
+ | enc_tem_k.enc.3.conv.conv | 9.248K | 0.226G |
866
+ | enc_tem_k.enc.3.conv.norm | 64 | 3.932M |
867
+ | enc_wind_q.enc | 28.32K | 1.125G |
868
+ | enc_wind_q.enc.0.conv | 0.384K | 88.08M |
869
+ | enc_wind_q.enc.0.conv.conv | 0.32K | 56.623M |
870
+ | enc_wind_q.enc.0.conv.norm | 64 | 31.457M |
871
+ | enc_wind_q.enc.1.conv | 9.312K | 0.461G |
872
+ | enc_wind_q.enc.1.conv.conv | 9.248K | 0.453G |
873
+ | enc_wind_q.enc.1.conv.norm | 64 | 7.864M |
874
+ | enc_wind_q.enc.2.conv | 9.312K | 0.461G |
875
+ | enc_wind_q.enc.2.conv.conv | 9.248K | 0.453G |
876
+ | enc_wind_q.enc.2.conv.norm | 64 | 7.864M |
877
+ | enc_wind_q.enc.3.conv | 9.312K | 0.115G |
878
+ | enc_wind_q.enc.3.conv.conv | 9.248K | 0.113G |
879
+ | enc_wind_q.enc.3.conv.norm | 64 | 1.966M |
880
+ | enc_wind_k.enc | 28.32K | 2.25G |
881
+ | enc_wind_k.enc.0.conv | 0.384K | 0.176G |
882
+ | enc_wind_k.enc.0.conv.conv | 0.32K | 0.113G |
883
+ | enc_wind_k.enc.0.conv.norm | 64 | 62.915M |
884
+ | enc_wind_k.enc.1.conv | 9.312K | 0.922G |
885
+ | enc_wind_k.enc.1.conv.conv | 9.248K | 0.906G |
886
+ | enc_wind_k.enc.1.conv.norm | 64 | 15.729M |
887
+ | enc_wind_k.enc.2.conv | 9.312K | 0.922G |
888
+ | enc_wind_k.enc.2.conv.conv | 9.248K | 0.906G |
889
+ | enc_wind_k.enc.2.conv.norm | 64 | 15.729M |
890
+ | enc_wind_k.enc.3.conv | 9.312K | 0.23G |
891
+ | enc_wind_k.enc.3.conv.conv | 9.248K | 0.226G |
892
+ | enc_wind_k.enc.3.conv.norm | 64 | 3.932M |
893
+ | dec_u10_q | 92.769K | 4.615G |
894
+ | dec_u10_q.dec | 92.736K | 4.608G |
895
+ | dec_u10_q.dec.0.conv | 37.056K | 0.461G |
896
+ | dec_u10_q.dec.1.conv | 9.312K | 0.461G |
897
+ | dec_u10_q.dec.2.conv | 37.056K | 1.843G |
898
+ | dec_u10_q.dec.3.conv | 9.312K | 1.843G |
899
+ | dec_u10_q.readout | 33 | 6.291M |
900
+ | dec_u10_q.readout.weight | (1, 32, 1, 1) | |
901
+ | dec_u10_q.readout.bias | (1,) | |
902
+ | dec_u10_k | 92.769K | 4.615G |
903
+ | dec_u10_k.dec | 92.736K | 4.608G |
904
+ | dec_u10_k.dec.0.conv | 37.056K | 0.461G |
905
+ | dec_u10_k.dec.1.conv | 9.312K | 0.461G |
906
+ | dec_u10_k.dec.2.conv | 37.056K | 1.843G |
907
+ | dec_u10_k.dec.3.conv | 9.312K | 1.843G |
908
+ | dec_u10_k.readout | 33 | 6.291M |
909
+ | dec_u10_k.readout.weight | (1, 32, 1, 1) | |
910
+ | dec_u10_k.readout.bias | (1,) | |
911
+ | dec_v10_q | 92.769K | 4.615G |
912
+ | dec_v10_q.dec | 92.736K | 4.608G |
913
+ | dec_v10_q.dec.0.conv | 37.056K | 0.461G |
914
+ | dec_v10_q.dec.1.conv | 9.312K | 0.461G |
915
+ | dec_v10_q.dec.2.conv | 37.056K | 1.843G |
916
+ | dec_v10_q.dec.3.conv | 9.312K | 1.843G |
917
+ | dec_v10_q.readout | 33 | 6.291M |
918
+ | dec_v10_q.readout.weight | (1, 32, 1, 1) | |
919
+ | dec_v10_q.readout.bias | (1,) | |
920
+ | dec_v10_k | 92.769K | 4.615G |
921
+ | dec_v10_k.dec | 92.736K | 4.608G |
922
+ | dec_v10_k.dec.0.conv | 37.056K | 0.461G |
923
+ | dec_v10_k.dec.1.conv | 9.312K | 0.461G |
924
+ | dec_v10_k.dec.2.conv | 37.056K | 1.843G |
925
+ | dec_v10_k.dec.3.conv | 9.312K | 1.843G |
926
+ | dec_v10_k.readout | 33 | 6.291M |
927
+ | dec_v10_k.readout.weight | (1, 32, 1, 1) | |
928
+ | dec_v10_k.readout.bias | (1,) | |
929
+ | dec_tem_q | 92.769K | 4.615G |
930
+ | dec_tem_q.dec | 92.736K | 4.608G |
931
+ | dec_tem_q.dec.0.conv | 37.056K | 0.461G |
932
+ | dec_tem_q.dec.1.conv | 9.312K | 0.461G |
933
+ | dec_tem_q.dec.2.conv | 37.056K | 1.843G |
934
+ | dec_tem_q.dec.3.conv | 9.312K | 1.843G |
935
+ | dec_tem_q.readout | 33 | 6.291M |
936
+ | dec_tem_q.readout.weight | (1, 32, 1, 1) | |
937
+ | dec_tem_q.readout.bias | (1,) | |
938
+ | dec_tem_k | 92.769K | 4.615G |
939
+ | dec_tem_k.dec | 92.736K | 4.608G |
940
+ | dec_tem_k.dec.0.conv | 37.056K | 0.461G |
941
+ | dec_tem_k.dec.1.conv | 9.312K | 0.461G |
942
+ | dec_tem_k.dec.2.conv | 37.056K | 1.843G |
943
+ | dec_tem_k.dec.3.conv | 9.312K | 1.843G |
944
+ | dec_tem_k.readout | 33 | 6.291M |
945
+ | dec_tem_k.readout.weight | (1, 32, 1, 1) | |
946
+ | dec_tem_k.readout.bias | (1,) | |
947
+ | dec_wind_q | 92.769K | 4.615G |
948
+ | dec_wind_q.dec | 92.736K | 4.608G |
949
+ | dec_wind_q.dec.0.conv | 37.056K | 0.461G |
950
+ | dec_wind_q.dec.1.conv | 9.312K | 0.461G |
951
+ | dec_wind_q.dec.2.conv | 37.056K | 1.843G |
952
+ | dec_wind_q.dec.3.conv | 9.312K | 1.843G |
953
+ | dec_wind_q.readout | 33 | 6.291M |
954
+ | dec_wind_q.readout.weight | (1, 32, 1, 1) | |
955
+ | dec_wind_q.readout.bias | (1,) | |
956
+ | dec_wind_k | 92.769K | 4.615G |
957
+ | dec_wind_k.dec | 92.736K | 4.608G |
958
+ | dec_wind_k.dec.0.conv | 37.056K | 0.461G |
959
+ | dec_wind_k.dec.1.conv | 9.312K | 0.461G |
960
+ | dec_wind_k.dec.2.conv | 37.056K | 1.843G |
961
+ | dec_wind_k.dec.3.conv | 9.312K | 1.843G |
962
+ | dec_wind_k.readout | 33 | 6.291M |
963
+ | dec_wind_k.readout.weight | (1, 32, 1, 1) | |
964
+ | dec_wind_k.readout.bias | (1,) | |
965
+ | hid_q | 8.418M | 34.352G |
966
+ | hid_q.conv1 | 98.56K | 0.403G |
967
+ | hid_q.conv1.weight | (256, 384, 1, 1) | |
968
+ | hid_q.conv1.bias | (256,) | |
969
+ | hid_q.layers | 8.221M | 33.546G |
970
+ | hid_q.layers.0 | 1.028M | 4.193G |
971
+ | hid_q.layers.1 | 1.028M | 4.193G |
972
+ | hid_q.layers.2 | 1.028M | 4.193G |
973
+ | hid_q.layers.3 | 1.028M | 4.193G |
974
+ | hid_q.layers.4 | 1.028M | 4.193G |
975
+ | hid_q.layers.5 | 1.028M | 4.193G |
976
+ | hid_q.layers.6 | 1.028M | 4.193G |
977
+ | hid_q.layers.7 | 1.028M | 4.193G |
978
+ | hid_q.conv2 | 98.688K | 0.403G |
979
+ | hid_q.conv2.weight | (384, 256, 1, 1) | |
980
+ | hid_q.conv2.bias | (384,) | |
981
+ | hid_k | 8.418M | 34.352G |
982
+ | hid_k.conv1 | 98.56K | 0.403G |
983
+ | hid_k.conv1.weight | (256, 384, 1, 1) | |
984
+ | hid_k.conv1.bias | (256,) | |
985
+ | hid_k.layers | 8.221M | 33.546G |
986
+ | hid_k.layers.0 | 1.028M | 4.193G |
987
+ | hid_k.layers.1 | 1.028M | 4.193G |
988
+ | hid_k.layers.2 | 1.028M | 4.193G |
989
+ | hid_k.layers.3 | 1.028M | 4.193G |
990
+ | hid_k.layers.4 | 1.028M | 4.193G |
991
+ | hid_k.layers.5 | 1.028M | 4.193G |
992
+ | hid_k.layers.6 | 1.028M | 4.193G |
993
+ | hid_k.layers.7 | 1.028M | 4.193G |
994
+ | hid_k.conv2 | 98.688K | 0.403G |
995
+ | hid_k.conv2.weight | (384, 256, 1, 1) | |
996
+ | hid_k.conv2.bias | (384,) | |
997
+ --------------------------------------------------------------------------------
998
+
999
+ 2025-03-04 10:34:50,323 - w1 : 53.3601556316129 | w2 : 1.1682677586641672 | w3 : 0.44011046531469966
1000
+ 2025-03-04 10:43:20,991 - Epoch 1: Lr: 0.0009999 | Train Loss: 0.0019597 | Vali Loss: 0.0007887
1001
+ 2025-03-04 10:51:55,047 - Epoch 2: Lr: 0.0009998 | Train Loss: 0.0006590 | Vali Loss: 0.0006095
1002
+ 2025-03-04 11:00:26,184 - Epoch 3: Lr: 0.0009994 | Train Loss: 0.0005067 | Vali Loss: 0.0005165
1003
+ 2025-03-04 11:08:59,422 - Epoch 4: Lr: 0.0009990 | Train Loss: 0.0004522 | Vali Loss: 0.0004847
1004
+ 2025-03-04 11:17:31,053 - Epoch 5: Lr: 0.0009985 | Train Loss: 0.0004065 | Vali Loss: 0.0003397
1005
+ 2025-03-04 11:26:02,869 - Epoch 6: Lr: 0.0009978 | Train Loss: 0.0003649 | Vali Loss: 0.0003139
1006
+ 2025-03-04 11:34:35,897 - Epoch 7: Lr: 0.0009970 | Train Loss: 0.0003061 | Vali Loss: 0.0003082
1007
+ 2025-03-04 11:43:08,691 - Epoch 8: Lr: 0.0009961 | Train Loss: 0.0002690 | Vali Loss: 0.0003194
1008
+ 2025-03-04 11:51:40,761 - Epoch 9: Lr: 0.0009950 | Train Loss: 0.0002419 | Vali Loss: 0.0002391
1009
+ 2025-03-04 12:00:12,479 - Epoch 10: Lr: 0.0009939 | Train Loss: 0.0002234 | Vali Loss: 0.0002504
1010
+ 2025-03-04 12:08:44,117 - Epoch 11: Lr: 0.0009926 | Train Loss: 0.0002062 | Vali Loss: 0.0002520
1011
+ 2025-03-04 12:17:14,734 - Epoch 12: Lr: 0.0009912 | Train Loss: 0.0002013 | Vali Loss: 0.0002697
1012
+ 2025-03-04 12:25:46,433 - Epoch 13: Lr: 0.0009896 | Train Loss: 0.0001873 | Vali Loss: 0.0002075
1013
+ 2025-03-04 12:34:19,574 - Epoch 14: Lr: 0.0009880 | Train Loss: 0.0001785 | Vali Loss: 0.0002301
1014
+ 2025-03-04 12:42:51,576 - Epoch 15: Lr: 0.0009862 | Train Loss: 0.0001732 | Vali Loss: 0.0002138
1015
+ 2025-03-04 12:51:22,061 - Epoch 16: Lr: 0.0009843 | Train Loss: 0.0001653 | Vali Loss: 0.0002172
1016
+ 2025-03-04 12:59:51,969 - Epoch 17: Lr: 0.0009823 | Train Loss: 0.0001607 | Vali Loss: 0.0002079
1017
+ 2025-03-04 13:08:24,723 - Epoch 18: Lr: 0.0009802 | Train Loss: 0.0001564 | Vali Loss: 0.0002001
1018
+ 2025-03-04 13:16:57,697 - Epoch 19: Lr: 0.0009779 | Train Loss: 0.0001527 | Vali Loss: 0.0002137
1019
+ 2025-03-04 13:25:29,862 - Epoch 20: Lr: 0.0009756 | Train Loss: 0.0001488 | Vali Loss: 0.0002374
1020
+ 2025-03-04 13:34:03,550 - Epoch 21: Lr: 0.0009731 | Train Loss: 0.0001458 | Vali Loss: 0.0001922
1021
+ 2025-03-04 13:42:35,566 - Epoch 22: Lr: 0.0009705 | Train Loss: 0.0001429 | Vali Loss: 0.0002037
1022
+ 2025-03-04 13:51:08,774 - Epoch 23: Lr: 0.0009678 | Train Loss: 0.0001397 | Vali Loss: 0.0001998
1023
+ 2025-03-04 13:59:41,807 - Epoch 24: Lr: 0.0009649 | Train Loss: 0.0001387 | Vali Loss: 0.0002705
1024
+ 2025-03-04 14:08:14,554 - Epoch 25: Lr: 0.0009620 | Train Loss: 0.0001351 | Vali Loss: 0.0001913
1025
+ 2025-03-04 14:16:47,258 - Epoch 26: Lr: 0.0009589 | Train Loss: 0.0001337 | Vali Loss: 0.0001865
1026
+ 2025-03-04 14:25:22,179 - Epoch 27: Lr: 0.0009557 | Train Loss: 0.0001318 | Vali Loss: 0.0001923
1027
+ 2025-03-04 14:33:54,843 - Epoch 28: Lr: 0.0009525 | Train Loss: 0.0001299 | Vali Loss: 0.0002024
1028
+ 2025-03-04 14:42:26,661 - Epoch 29: Lr: 0.0009491 | Train Loss: 0.0001277 | Vali Loss: 0.0001773
1029
+ 2025-03-04 14:50:59,235 - Epoch 30: Lr: 0.0009456 | Train Loss: 0.0001262 | Vali Loss: 0.0002047
1030
+ 2025-03-04 14:59:31,332 - Epoch 31: Lr: 0.0009419 | Train Loss: 0.0001252 | Vali Loss: 0.0001800
1031
+ 2025-03-04 15:08:03,760 - Epoch 32: Lr: 0.0009382 | Train Loss: 0.0001231 | Vali Loss: 0.0001810
1032
+ 2025-03-04 15:16:36,558 - Epoch 33: Lr: 0.0009344 | Train Loss: 0.0001219 | Vali Loss: 0.0001927
1033
+ 2025-03-04 15:25:11,396 - Epoch 34: Lr: 0.0009304 | Train Loss: 0.0001217 | Vali Loss: 0.0001796
1034
+ 2025-03-04 15:33:42,965 - Epoch 35: Lr: 0.0009264 | Train Loss: 0.0001195 | Vali Loss: 0.0001837
1035
+ 2025-03-04 15:42:17,189 - Epoch 36: Lr: 0.0009222 | Train Loss: 0.0001188 | Vali Loss: 0.0001824
1036
+ 2025-03-04 15:50:49,733 - Epoch 37: Lr: 0.0009180 | Train Loss: 0.0001174 | Vali Loss: 0.0001825
1037
+ 2025-03-04 15:59:21,575 - Epoch 38: Lr: 0.0009136 | Train Loss: 0.0001159 | Vali Loss: 0.0002027
1038
+ 2025-03-04 16:07:53,148 - Epoch 39: Lr: 0.0009092 | Train Loss: 0.0001142 | Vali Loss: 0.0001734
1039
+ 2025-03-04 16:16:27,749 - Epoch 40: Lr: 0.0009046 | Train Loss: 0.0001140 | Vali Loss: 0.0001820
1040
+ 2025-03-04 16:25:02,071 - Epoch 41: Lr: 0.0008999 | Train Loss: 0.0001132 | Vali Loss: 0.0001742
1041
+ 2025-03-04 16:33:34,367 - Epoch 42: Lr: 0.0008952 | Train Loss: 0.0001122 | Vali Loss: 0.0001760
1042
+ 2025-03-04 16:42:06,752 - Epoch 43: Lr: 0.0008903 | Train Loss: 0.0001114 | Vali Loss: 0.0001692
1043
+ 2025-03-04 16:50:40,277 - Epoch 44: Lr: 0.0008854 | Train Loss: 0.0001099 | Vali Loss: 0.0001692
1044
+ 2025-03-04 16:59:11,219 - Epoch 45: Lr: 0.0008803 | Train Loss: 0.0001096 | Vali Loss: 0.0001717
1045
+ 2025-03-04 17:07:42,601 - Epoch 46: Lr: 0.0008752 | Train Loss: 0.0001083 | Vali Loss: 0.0001811
1046
+ 2025-03-04 17:16:13,459 - Epoch 47: Lr: 0.0008699 | Train Loss: 0.0001078 | Vali Loss: 0.0001766
1047
+ 2025-03-04 17:24:44,903 - Epoch 48: Lr: 0.0008646 | Train Loss: 0.0001075 | Vali Loss: 0.0001705
1048
+ 2025-03-04 17:33:15,786 - Epoch 49: Lr: 0.0008592 | Train Loss: 0.0001062 | Vali Loss: 0.0001826
1049
+ 2025-03-04 17:41:49,059 - Epoch 50: Lr: 0.0008537 | Train Loss: 0.0001060 | Vali Loss: 0.0001761
1050
+ 2025-03-04 17:50:20,455 - Epoch 51: Lr: 0.0008481 | Train Loss: 0.0001053 | Vali Loss: 0.0001809
1051
+ 2025-03-04 17:58:53,837 - Epoch 52: Lr: 0.0008424 | Train Loss: 0.0001039 | Vali Loss: 0.0001697
1052
+ 2025-03-04 18:07:26,857 - Epoch 53: Lr: 0.0008367 | Train Loss: 0.0001038 | Vali Loss: 0.0001720
1053
+ 2025-03-04 18:15:58,239 - Epoch 54: Lr: 0.0008308 | Train Loss: 0.0001029 | Vali Loss: 0.0001735
1054
+ 2025-03-04 18:24:29,313 - Epoch 55: Lr: 0.0008249 | Train Loss: 0.0001023 | Vali Loss: 0.0001693
1055
+ 2025-03-04 18:33:00,459 - Epoch 56: Lr: 0.0008189 | Train Loss: 0.0001018 | Vali Loss: 0.0001812
1056
+ 2025-03-04 18:41:33,233 - Epoch 57: Lr: 0.0008128 | Train Loss: 0.0001015 | Vali Loss: 0.0001704
1057
+ 2025-03-04 18:50:06,231 - Epoch 58: Lr: 0.0008066 | Train Loss: 0.0001005 | Vali Loss: 0.0001736
1058
+ 2025-03-04 18:58:38,422 - Epoch 59: Lr: 0.0008004 | Train Loss: 0.0001002 | Vali Loss: 0.0001671
1059
+ 2025-03-04 19:07:11,926 - Epoch 60: Lr: 0.0007941 | Train Loss: 0.0000993 | Vali Loss: 0.0001636
1060
+ 2025-03-04 19:15:43,611 - Epoch 61: Lr: 0.0007877 | Train Loss: 0.0000987 | Vali Loss: 0.0001725
1061
+ 2025-03-04 19:24:16,109 - Epoch 62: Lr: 0.0007813 | Train Loss: 0.0000977 | Vali Loss: 0.0001684
1062
+ 2025-03-04 19:32:47,044 - Epoch 63: Lr: 0.0007747 | Train Loss: 0.0000970 | Vali Loss: 0.0001648
1063
+ 2025-03-04 19:41:18,301 - Epoch 64: Lr: 0.0007681 | Train Loss: 0.0000972 | Vali Loss: 0.0001608
1064
+ 2025-03-04 19:49:50,247 - Epoch 65: Lr: 0.0007615 | Train Loss: 0.0000964 | Vali Loss: 0.0001672
1065
+ 2025-03-04 19:58:24,129 - Epoch 66: Lr: 0.0007548 | Train Loss: 0.0000955 | Vali Loss: 0.0001650
1066
+ 2025-03-04 20:06:55,456 - Epoch 67: Lr: 0.0007480 | Train Loss: 0.0000952 | Vali Loss: 0.0001689
1067
+ 2025-03-04 20:15:28,277 - Epoch 68: Lr: 0.0007411 | Train Loss: 0.0000948 | Vali Loss: 0.0001627
1068
+ 2025-03-04 20:23:59,746 - Epoch 69: Lr: 0.0007342 | Train Loss: 0.0000940 | Vali Loss: 0.0001594
1069
+ 2025-03-04 20:32:31,013 - Epoch 70: Lr: 0.0007273 | Train Loss: 0.0000931 | Vali Loss: 0.0001616
1070
+ 2025-03-04 20:41:02,553 - Epoch 71: Lr: 0.0007202 | Train Loss: 0.0000927 | Vali Loss: 0.0001712
1071
+ 2025-03-04 20:49:34,727 - Epoch 72: Lr: 0.0007132 | Train Loss: 0.0000922 | Vali Loss: 0.0001696
1072
+ 2025-03-04 20:58:06,075 - Epoch 73: Lr: 0.0007061 | Train Loss: 0.0000918 | Vali Loss: 0.0001613
1073
+ 2025-03-04 21:06:37,758 - Epoch 74: Lr: 0.0006989 | Train Loss: 0.0000905 | Vali Loss: 0.0001664
1074
+ 2025-03-04 21:15:09,643 - Epoch 75: Lr: 0.0006917 | Train Loss: 0.0000907 | Vali Loss: 0.0001667
1075
+ 2025-03-04 21:23:40,793 - Epoch 76: Lr: 0.0006844 | Train Loss: 0.0000898 | Vali Loss: 0.0001629
1076
+ 2025-03-04 21:32:13,249 - Epoch 77: Lr: 0.0006771 | Train Loss: 0.0000894 | Vali Loss: 0.0001682
1077
+ 2025-03-04 21:40:44,457 - Epoch 78: Lr: 0.0006697 | Train Loss: 0.0000894 | Vali Loss: 0.0001578
1078
+ 2025-03-04 21:49:17,513 - Epoch 79: Lr: 0.0006623 | Train Loss: 0.0000886 | Vali Loss: 0.0001593
1079
+ 2025-03-04 21:57:51,556 - Epoch 80: Lr: 0.0006549 | Train Loss: 0.0000880 | Vali Loss: 0.0001569
1080
+ 2025-03-04 22:06:22,825 - Epoch 81: Lr: 0.0006474 | Train Loss: 0.0000874 | Vali Loss: 0.0001605
1081
+ 2025-03-04 22:14:54,714 - Epoch 82: Lr: 0.0006399 | Train Loss: 0.0000873 | Vali Loss: 0.0001575
1082
+ 2025-03-04 22:23:27,832 - Epoch 83: Lr: 0.0006323 | Train Loss: 0.0000868 | Vali Loss: 0.0001574
1083
+ 2025-03-04 22:32:00,568 - Epoch 84: Lr: 0.0006247 | Train Loss: 0.0000862 | Vali Loss: 0.0001613
1084
+ 2025-03-04 22:40:33,828 - Epoch 85: Lr: 0.0006171 | Train Loss: 0.0000861 | Vali Loss: 0.0001632
1085
+ 2025-03-04 22:49:07,400 - Epoch 86: Lr: 0.0006095 | Train Loss: 0.0000858 | Vali Loss: 0.0001598
1086
+ 2025-03-04 22:57:38,732 - Epoch 87: Lr: 0.0006018 | Train Loss: 0.0000852 | Vali Loss: 0.0001592
1087
+ 2025-03-04 23:06:09,817 - Epoch 88: Lr: 0.0005941 | Train Loss: 0.0000850 | Vali Loss: 0.0001565
1088
+ 2025-03-04 23:14:40,669 - Epoch 89: Lr: 0.0005864 | Train Loss: 0.0000850 | Vali Loss: 0.0001544
1089
+ 2025-03-04 23:23:14,270 - Epoch 90: Lr: 0.0005786 | Train Loss: 0.0000845 | Vali Loss: 0.0001578
1090
+ 2025-03-04 23:31:44,147 - Epoch 91: Lr: 0.0005709 | Train Loss: 0.0000838 | Vali Loss: 0.0001528
1091
+ 2025-03-04 23:40:15,125 - Epoch 92: Lr: 0.0005631 | Train Loss: 0.0000837 | Vali Loss: 0.0001563
1092
+ 2025-03-04 23:48:45,261 - Epoch 93: Lr: 0.0005553 | Train Loss: 0.0000831 | Vali Loss: 0.0001620
1093
+ 2025-03-04 23:57:14,890 - Epoch 94: Lr: 0.0005475 | Train Loss: 0.0000832 | Vali Loss: 0.0001531
1094
+ 2025-03-05 00:05:44,892 - Epoch 95: Lr: 0.0005397 | Train Loss: 0.0000829 | Vali Loss: 0.0001555
1095
+ 2025-03-05 00:14:17,904 - Epoch 96: Lr: 0.0005319 | Train Loss: 0.0000826 | Vali Loss: 0.0001528
1096
+ 2025-03-05 00:22:48,128 - Epoch 97: Lr: 0.0005240 | Train Loss: 0.0000823 | Vali Loss: 0.0001665
1097
+ 2025-03-05 00:31:19,082 - Epoch 98: Lr: 0.0005162 | Train Loss: 0.0000823 | Vali Loss: 0.0001564
1098
+ 2025-03-05 00:39:51,294 - Epoch 99: Lr: 0.0005083 | Train Loss: 0.0000820 | Vali Loss: 0.0001522
1099
+ 2025-03-05 00:48:25,177 - Epoch 100: Lr: 0.0005005 | Train Loss: 0.0000815 | Vali Loss: 0.0001536
1100
+ 2025-03-05 00:56:57,631 - Epoch 101: Lr: 0.0004927 | Train Loss: 0.0000812 | Vali Loss: 0.0001569
1101
+ 2025-03-05 01:05:29,325 - Epoch 102: Lr: 0.0004848 | Train Loss: 0.0000813 | Vali Loss: 0.0001540
1102
+ 2025-03-05 01:14:01,107 - Epoch 103: Lr: 0.0004770 | Train Loss: 0.0000811 | Vali Loss: 0.0001570
1103
+ 2025-03-05 01:22:31,745 - Epoch 104: Lr: 0.0004691 | Train Loss: 0.0000810 | Vali Loss: 0.0001526
1104
+ 2025-03-05 01:31:02,664 - Epoch 105: Lr: 0.0004613 | Train Loss: 0.0000805 | Vali Loss: 0.0001545
1105
+ 2025-03-05 01:39:35,952 - Epoch 106: Lr: 0.0004535 | Train Loss: 0.0000804 | Vali Loss: 0.0001527
1106
+ 2025-03-05 01:48:06,680 - Epoch 107: Lr: 0.0004457 | Train Loss: 0.0000798 | Vali Loss: 0.0001528
1107
+ 2025-03-05 01:56:37,750 - Epoch 108: Lr: 0.0004379 | Train Loss: 0.0000800 | Vali Loss: 0.0001530
1108
+ 2025-03-05 02:05:08,748 - Epoch 109: Lr: 0.0004301 | Train Loss: 0.0000797 | Vali Loss: 0.0001535
1109
+ 2025-03-05 02:13:43,051 - Epoch 110: Lr: 0.0004224 | Train Loss: 0.0000796 | Vali Loss: 0.0001607
1110
+ 2025-03-05 02:22:15,393 - Epoch 111: Lr: 0.0004146 | Train Loss: 0.0000795 | Vali Loss: 0.0001532
1111
+ 2025-03-05 02:30:47,531 - Epoch 112: Lr: 0.0004069 | Train Loss: 0.0000793 | Vali Loss: 0.0001550
1112
+ 2025-03-05 02:39:20,640 - Epoch 113: Lr: 0.0003992 | Train Loss: 0.0000793 | Vali Loss: 0.0001572
1113
+ 2025-03-05 02:47:53,205 - Epoch 114: Lr: 0.0003915 | Train Loss: 0.0000789 | Vali Loss: 0.0001528
1114
+ 2025-03-05 02:56:25,710 - Epoch 115: Lr: 0.0003839 | Train Loss: 0.0000786 | Vali Loss: 0.0001514
1115
+ 2025-03-05 03:05:00,336 - Epoch 116: Lr: 0.0003763 | Train Loss: 0.0000788 | Vali Loss: 0.0001521
1116
+ 2025-03-05 03:13:32,225 - Epoch 117: Lr: 0.0003687 | Train Loss: 0.0000785 | Vali Loss: 0.0001532
1117
+ 2025-03-05 03:22:05,490 - Epoch 118: Lr: 0.0003611 | Train Loss: 0.0000782 | Vali Loss: 0.0001582
1118
+ 2025-03-05 03:30:38,011 - Epoch 119: Lr: 0.0003536 | Train Loss: 0.0000784 | Vali Loss: 0.0001545
1119
+ 2025-03-05 03:39:09,974 - Epoch 120: Lr: 0.0003461 | Train Loss: 0.0000782 | Vali Loss: 0.0001510
1120
+ 2025-03-05 03:47:42,644 - Epoch 121: Lr: 0.0003387 | Train Loss: 0.0000780 | Vali Loss: 0.0001518
1121
+ 2025-03-05 03:56:14,100 - Epoch 122: Lr: 0.0003313 | Train Loss: 0.0000777 | Vali Loss: 0.0001541
1122
+ 2025-03-05 04:04:46,621 - Epoch 123: Lr: 0.0003239 | Train Loss: 0.0000776 | Vali Loss: 0.0001528
1123
+ 2025-03-05 04:13:21,788 - Epoch 124: Lr: 0.0003166 | Train Loss: 0.0000774 | Vali Loss: 0.0001515
1124
+ 2025-03-05 04:21:52,163 - Epoch 125: Lr: 0.0003093 | Train Loss: 0.0000773 | Vali Loss: 0.0001550
1125
+ 2025-03-05 04:30:26,772 - Epoch 126: Lr: 0.0003021 | Train Loss: 0.0000773 | Vali Loss: 0.0001485
1126
+ 2025-03-05 04:39:00,837 - Epoch 127: Lr: 0.0002949 | Train Loss: 0.0000773 | Vali Loss: 0.0001532
1127
+ 2025-03-05 04:47:29,703 - Epoch 128: Lr: 0.0002878 | Train Loss: 0.0000770 | Vali Loss: 0.0001563
1128
+ 2025-03-05 04:55:58,650 - Epoch 129: Lr: 0.0002808 | Train Loss: 0.0000770 | Vali Loss: 0.0001498
1129
+ 2025-03-05 05:04:30,592 - Epoch 130: Lr: 0.0002737 | Train Loss: 0.0000769 | Vali Loss: 0.0001498
1130
+ 2025-03-05 05:13:03,384 - Epoch 131: Lr: 0.0002668 | Train Loss: 0.0000768 | Vali Loss: 0.0001510
1131
+ 2025-03-05 05:21:34,940 - Epoch 132: Lr: 0.0002599 | Train Loss: 0.0000765 | Vali Loss: 0.0001507
1132
+ 2025-03-05 05:30:05,265 - Epoch 133: Lr: 0.0002530 | Train Loss: 0.0000766 | Vali Loss: 0.0001519
1133
+ 2025-03-05 05:38:37,142 - Epoch 134: Lr: 0.0002462 | Train Loss: 0.0000764 | Vali Loss: 0.0001516
1134
+ 2025-03-05 05:47:11,090 - Epoch 135: Lr: 0.0002395 | Train Loss: 0.0000764 | Vali Loss: 0.0001503
1135
+ 2025-03-05 05:55:42,561 - Epoch 136: Lr: 0.0002329 | Train Loss: 0.0000761 | Vali Loss: 0.0001497
1136
+ 2025-03-05 06:04:12,557 - Epoch 137: Lr: 0.0002263 | Train Loss: 0.0000762 | Vali Loss: 0.0001505
1137
+ 2025-03-05 06:12:43,986 - Epoch 138: Lr: 0.0002197 | Train Loss: 0.0000759 | Vali Loss: 0.0001499
1138
+ 2025-03-05 06:21:14,517 - Epoch 139: Lr: 0.0002133 | Train Loss: 0.0000759 | Vali Loss: 0.0001479
1139
+ 2025-03-05 06:29:45,384 - Epoch 140: Lr: 0.0002069 | Train Loss: 0.0000757 | Vali Loss: 0.0001496
1140
+ 2025-03-05 06:38:17,296 - Epoch 141: Lr: 0.0002006 | Train Loss: 0.0000758 | Vali Loss: 0.0001507
1141
+ 2025-03-05 06:46:48,200 - Epoch 142: Lr: 0.0001944 | Train Loss: 0.0000755 | Vali Loss: 0.0001490
1142
+ 2025-03-05 06:55:20,743 - Epoch 143: Lr: 0.0001882 | Train Loss: 0.0000754 | Vali Loss: 0.0001502
1143
+ 2025-03-05 07:03:51,667 - Epoch 144: Lr: 0.0001821 | Train Loss: 0.0000755 | Vali Loss: 0.0001495
1144
+ 2025-03-05 07:12:23,488 - Epoch 145: Lr: 0.0001761 | Train Loss: 0.0000753 | Vali Loss: 0.0001476
1145
+ 2025-03-05 07:20:55,438 - Epoch 146: Lr: 0.0001702 | Train Loss: 0.0000752 | Vali Loss: 0.0001501
1146
+ 2025-03-05 07:29:29,613 - Epoch 147: Lr: 0.0001643 | Train Loss: 0.0000753 | Vali Loss: 0.0001502
1147
+ 2025-03-05 07:38:01,058 - Epoch 148: Lr: 0.0001586 | Train Loss: 0.0000752 | Vali Loss: 0.0001500
1148
+ 2025-03-05 07:46:33,336 - Epoch 149: Lr: 0.0001529 | Train Loss: 0.0000751 | Vali Loss: 0.0001498
1149
+ 2025-03-05 07:55:04,008 - Epoch 150: Lr: 0.0001473 | Train Loss: 0.0000751 | Vali Loss: 0.0001487
1150
+ 2025-03-05 08:03:35,043 - Epoch 151: Lr: 0.0001418 | Train Loss: 0.0000750 | Vali Loss: 0.0001487
1151
+ 2025-03-05 08:12:06,254 - Epoch 152: Lr: 0.0001364 | Train Loss: 0.0000749 | Vali Loss: 0.0001492
1152
+ 2025-03-05 08:20:36,593 - Epoch 153: Lr: 0.0001311 | Train Loss: 0.0000748 | Vali Loss: 0.0001506
1153
+ 2025-03-05 08:29:07,219 - Epoch 154: Lr: 0.0001258 | Train Loss: 0.0000748 | Vali Loss: 0.0001483
1154
+ 2025-03-05 08:37:38,816 - Epoch 155: Lr: 0.0001207 | Train Loss: 0.0000746 | Vali Loss: 0.0001508
1155
+ 2025-03-05 08:46:10,630 - Epoch 156: Lr: 0.0001156 | Train Loss: 0.0000745 | Vali Loss: 0.0001487
1156
+ 2025-03-05 08:54:41,322 - Epoch 157: Lr: 0.0001107 | Train Loss: 0.0000745 | Vali Loss: 0.0001505
1157
+ 2025-03-05 09:03:12,228 - Epoch 158: Lr: 0.0001058 | Train Loss: 0.0000745 | Vali Loss: 0.0001491
1158
+ 2025-03-05 09:11:42,582 - Epoch 159: Lr: 0.0001011 | Train Loss: 0.0000743 | Vali Loss: 0.0001498
1159
+ 2025-03-05 09:20:14,859 - Epoch 160: Lr: 0.0000964 | Train Loss: 0.0000743 | Vali Loss: 0.0001489
1160
+ 2025-03-05 09:28:46,206 - Epoch 161: Lr: 0.0000918 | Train Loss: 0.0000744 | Vali Loss: 0.0001474
1161
+ 2025-03-05 09:37:17,322 - Epoch 162: Lr: 0.0000874 | Train Loss: 0.0000743 | Vali Loss: 0.0001492
1162
+ 2025-03-05 09:45:47,828 - Epoch 163: Lr: 0.0000830 | Train Loss: 0.0000741 | Vali Loss: 0.0001479
1163
+ 2025-03-05 09:54:17,957 - Epoch 164: Lr: 0.0000788 | Train Loss: 0.0000744 | Vali Loss: 0.0001473
1164
+ 2025-03-05 10:02:51,191 - Epoch 165: Lr: 0.0000746 | Train Loss: 0.0000743 | Vali Loss: 0.0001484
1165
+ 2025-03-05 10:11:21,356 - Epoch 166: Lr: 0.0000706 | Train Loss: 0.0000740 | Vali Loss: 0.0001479
1166
+ 2025-03-05 10:19:53,279 - Epoch 167: Lr: 0.0000666 | Train Loss: 0.0000741 | Vali Loss: 0.0001482
1167
+ 2025-03-05 10:28:24,157 - Epoch 168: Lr: 0.0000628 | Train Loss: 0.0000739 | Vali Loss: 0.0001495
1168
+ 2025-03-05 10:36:57,308 - Epoch 169: Lr: 0.0000591 | Train Loss: 0.0000738 | Vali Loss: 0.0001487
1169
+ 2025-03-05 10:45:27,704 - Epoch 170: Lr: 0.0000554 | Train Loss: 0.0000739 | Vali Loss: 0.0001488
1170
+ 2025-03-05 10:54:01,368 - Epoch 171: Lr: 0.0000519 | Train Loss: 0.0000739 | Vali Loss: 0.0001474
1171
+ 2025-03-05 11:02:33,907 - Epoch 172: Lr: 0.0000485 | Train Loss: 0.0000740 | Vali Loss: 0.0001490
1172
+ 2025-03-05 11:11:04,994 - Epoch 173: Lr: 0.0000453 | Train Loss: 0.0000738 | Vali Loss: 0.0001479
1173
+ 2025-03-05 11:19:35,898 - Epoch 174: Lr: 0.0000421 | Train Loss: 0.0000739 | Vali Loss: 0.0001484
1174
+ 2025-03-05 11:28:08,630 - Epoch 175: Lr: 0.0000390 | Train Loss: 0.0000738 | Vali Loss: 0.0001482
1175
+ 2025-03-05 11:36:41,603 - Epoch 176: Lr: 0.0000361 | Train Loss: 0.0000738 | Vali Loss: 0.0001483
1176
+ 2025-03-05 11:45:12,970 - Epoch 177: Lr: 0.0000332 | Train Loss: 0.0000736 | Vali Loss: 0.0001480
1177
+ 2025-03-05 11:53:45,258 - Epoch 178: Lr: 0.0000305 | Train Loss: 0.0000735 | Vali Loss: 0.0001475
1178
+ 2025-03-05 12:02:16,556 - Epoch 179: Lr: 0.0000279 | Train Loss: 0.0000736 | Vali Loss: 0.0001480
1179
+ 2025-03-05 12:10:50,011 - Epoch 180: Lr: 0.0000254 | Train Loss: 0.0000736 | Vali Loss: 0.0001471
1180
+ 2025-03-05 12:19:22,948 - Epoch 181: Lr: 0.0000231 | Train Loss: 0.0000737 | Vali Loss: 0.0001481
1181
+ 2025-03-05 12:27:54,914 - Epoch 182: Lr: 0.0000208 | Train Loss: 0.0000734 | Vali Loss: 0.0001478
1182
+ 2025-03-05 12:36:27,787 - Epoch 183: Lr: 0.0000187 | Train Loss: 0.0000734 | Vali Loss: 0.0001478
1183
+ 2025-03-05 12:45:00,089 - Epoch 184: Lr: 0.0000167 | Train Loss: 0.0000734 | Vali Loss: 0.0001475
1184
+ 2025-03-05 12:53:29,748 - Epoch 185: Lr: 0.0000148 | Train Loss: 0.0000734 | Vali Loss: 0.0001473
1185
+ 2025-03-05 13:02:00,718 - Epoch 186: Lr: 0.0000130 | Train Loss: 0.0000733 | Vali Loss: 0.0001476
1186
+ 2025-03-05 13:10:33,296 - Epoch 187: Lr: 0.0000114 | Train Loss: 0.0000735 | Vali Loss: 0.0001471
1187
+ 2025-03-05 13:19:05,137 - Epoch 188: Lr: 0.0000098 | Train Loss: 0.0000732 | Vali Loss: 0.0001476
1188
+ 2025-03-05 13:27:37,895 - Epoch 189: Lr: 0.0000084 | Train Loss: 0.0000733 | Vali Loss: 0.0001473
1189
+ 2025-03-05 13:36:10,001 - Epoch 190: Lr: 0.0000071 | Train Loss: 0.0000733 | Vali Loss: 0.0001471
1190
+ 2025-03-05 13:44:43,574 - Epoch 191: Lr: 0.0000060 | Train Loss: 0.0000731 | Vali Loss: 0.0001476
1191
+ 2025-03-05 13:53:15,516 - Epoch 192: Lr: 0.0000049 | Train Loss: 0.0000733 | Vali Loss: 0.0001476
1192
+ 2025-03-05 14:01:47,621 - Epoch 193: Lr: 0.0000040 | Train Loss: 0.0000734 | Vali Loss: 0.0001480
1193
+ 2025-03-05 14:10:18,870 - Epoch 194: Lr: 0.0000032 | Train Loss: 0.0000732 | Vali Loss: 0.0001471
1194
+ 2025-03-05 14:18:48,662 - Epoch 195: Lr: 0.0000025 | Train Loss: 0.0000734 | Vali Loss: 0.0001474
1195
+ 2025-03-05 14:27:21,744 - Epoch 196: Lr: 0.0000020 | Train Loss: 0.0000732 | Vali Loss: 0.0001475
1196
+ 2025-03-05 14:35:53,436 - Epoch 197: Lr: 0.0000016 | Train Loss: 0.0000733 | Vali Loss: 0.0001473
1197
+ 2025-03-05 14:44:26,382 - Epoch 198: Lr: 0.0000012 | Train Loss: 0.0000732 | Vali Loss: 0.0001475
1198
+ 2025-03-05 14:52:59,224 - Epoch 199: Lr: 0.0000011 | Train Loss: 0.0000731 | Vali Loss: 0.0001474
1199
+ 2025-03-05 14:54:24,199 - mse:10.27510929107666, mae:546.082275390625, rmse:3.2054810523986816, ssim:0.9897105576420244, psnr:39.14245798289701