Hugging Face's logo

guaishou1
/
Met2Net

Model card Files
xet
Community
guaishou1 commited on
Commit
35694dc
·
verified ·
1 Parent(s): 2d94e1b

Upload MvMmfnist/test_20241112_174055.log with huggingface_hub

Browse files
Files changed (1) hide show
  1. MvMmfnist/test_20241112_174055.log +1014 -0
MvMmfnist/test_20241112_174055.log ADDED
@@ -0,0 +1,1014 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-11-12 17:40:56,140 - Environment info:
2
+ ------------------------------------------------------------
3
+ sys.platform: linux
4
+ Python: 3.10.8 (main, Nov 24 2022, 14:13:03) [GCC 11.2.0]
5
+ CUDA available: True
6
+ CUDA_HOME: /usr/local/cuda-10.1
7
+ NVCC: Cuda compilation tools, release 10.1, V10.1.243
8
+ GPU 0: NVIDIA A800 80GB PCIe
9
+ GCC: gcc (Ubuntu 7.4.0-1ubuntu1~18.04.1) 7.4.0
10
+ PyTorch: 2.3.0
11
+ PyTorch compiling details: PyTorch built with:
12
+ - GCC 9.3
13
+ - C++ Version: 201703
14
+ - Intel(R) oneAPI Math Kernel Library Version 2023.1-Product Build 20230303 for Intel(R) 64 architecture applications
15
+ - Intel(R) MKL-DNN v3.3.6 (Git Hash 86e6af5974177e513fd3fee58425e1063e7f1361)
16
+ - OpenMP 201511 (a.k.a. OpenMP 4.5)
17
+ - LAPACK is enabled (usually provided by MKL)
18
+ - NNPACK is enabled
19
+ - CPU capability usage: AVX2
20
+ - CUDA Runtime 12.1
21
+ - 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
22
+ - CuDNN 8.9.2
23
+ - Magma 2.6.1
24
+ - 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,
25
+
26
+ TorchVision: 0.18.0
27
+ OpenCV: 4.10.0
28
+ openstl: 1.0.0
29
+ ------------------------------------------------------------
30
+
31
+ 2024-11-12 17:40:56,332 -
32
+ device: cuda
33
+ dist: False
34
+ res_dir: work_dirs
35
+ ex_name: mv_mmnist/med3_ciatt_lr1e-3_m0_newdata
36
+ fp16: False
37
+ torchscript: False
38
+ seed: 42
39
+ fps: False
40
+ test: True
41
+ deterministic: False
42
+ batch_size: 16
43
+ val_batch_size: 16
44
+ num_workers: 4
45
+ data_root: /root/data/lsh/openstl_weather/openstl/data
46
+ dataname: mv_mmnist
47
+ pre_seq_length: 10
48
+ aft_seq_length: 10
49
+ total_length: 20
50
+ use_augment: False
51
+ use_prefetcher: False
52
+ drop_last: False
53
+ method: its
54
+ config_file: configs/mv_mmnist/its.py
55
+ model_type: TAU
56
+ drop: 0.0
57
+ drop_path: 0.0
58
+ overwrite: False
59
+ epoch: 200
60
+ log_step: 1
61
+ opt: adam
62
+ opt_eps: None
63
+ opt_betas: None
64
+ momentum: 0.9
65
+ weight_decay: 0.0
66
+ clip_grad: None
67
+ clip_mode: norm
68
+ no_display_method_info: False
69
+ sched: cosine
70
+ lr: 0.001
71
+ lr_k_decay: 1.0
72
+ warmup_lr: 1e-05
73
+ min_lr: 1e-06
74
+ final_div_factor: 10000.0
75
+ warmup_epoch: 0
76
+ decay_epoch: 100
77
+ decay_rate: 0.1
78
+ filter_bias_and_bn: False
79
+ gpus: [0]
80
+ metric_for_bestckpt: val_loss
81
+ ckpt_path: None
82
+ spatio_kernel_enc: 3
83
+ spatio_kernel_dec: 3
84
+ hid_S: 64
85
+ hid_T: 512
86
+ N_T: 8
87
+ N_S: 4
88
+ momentum_ema: 0
89
+ in_shape: [10, 3, 64, 64]
90
+ data_name: mv_mmnist
91
+ metrics: ['mse', 'mae', 'ssim', 'psnr']
92
+ 2024-11-12 17:40:56,333 - Model info:
93
+ SimVP_Model(
94
+ (enc_u10_q): Encoder(
95
+ (enc): Sequential(
96
+ (0): ConvSC(
97
+ (conv): BasicConv2d(
98
+ (conv): Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
99
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
100
+ (act): SiLU()
101
+ )
102
+ )
103
+ (1): ConvSC(
104
+ (conv): BasicConv2d(
105
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
106
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
107
+ (act): SiLU()
108
+ )
109
+ )
110
+ (2): ConvSC(
111
+ (conv): BasicConv2d(
112
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
113
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
114
+ (act): SiLU()
115
+ )
116
+ )
117
+ (3): ConvSC(
118
+ (conv): BasicConv2d(
119
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
120
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
121
+ (act): SiLU()
122
+ )
123
+ )
124
+ )
125
+ )
126
+ (enc_u10_k): Encoder(
127
+ (enc): Sequential(
128
+ (0): ConvSC(
129
+ (conv): BasicConv2d(
130
+ (conv): Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
131
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
132
+ (act): SiLU()
133
+ )
134
+ )
135
+ (1): ConvSC(
136
+ (conv): BasicConv2d(
137
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
138
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
139
+ (act): SiLU()
140
+ )
141
+ )
142
+ (2): ConvSC(
143
+ (conv): BasicConv2d(
144
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
145
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
146
+ (act): SiLU()
147
+ )
148
+ )
149
+ (3): ConvSC(
150
+ (conv): BasicConv2d(
151
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
152
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
153
+ (act): SiLU()
154
+ )
155
+ )
156
+ )
157
+ )
158
+ (enc_v10_q): Encoder(
159
+ (enc): Sequential(
160
+ (0): ConvSC(
161
+ (conv): BasicConv2d(
162
+ (conv): Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
163
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
164
+ (act): SiLU()
165
+ )
166
+ )
167
+ (1): ConvSC(
168
+ (conv): BasicConv2d(
169
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
170
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
171
+ (act): SiLU()
172
+ )
173
+ )
174
+ (2): ConvSC(
175
+ (conv): BasicConv2d(
176
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
177
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
178
+ (act): SiLU()
179
+ )
180
+ )
181
+ (3): ConvSC(
182
+ (conv): BasicConv2d(
183
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
184
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
185
+ (act): SiLU()
186
+ )
187
+ )
188
+ )
189
+ )
190
+ (enc_v10_k): Encoder(
191
+ (enc): Sequential(
192
+ (0): ConvSC(
193
+ (conv): BasicConv2d(
194
+ (conv): Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
195
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
196
+ (act): SiLU()
197
+ )
198
+ )
199
+ (1): ConvSC(
200
+ (conv): BasicConv2d(
201
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
202
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
203
+ (act): SiLU()
204
+ )
205
+ )
206
+ (2): ConvSC(
207
+ (conv): BasicConv2d(
208
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
209
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
210
+ (act): SiLU()
211
+ )
212
+ )
213
+ (3): ConvSC(
214
+ (conv): BasicConv2d(
215
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
216
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
217
+ (act): SiLU()
218
+ )
219
+ )
220
+ )
221
+ )
222
+ (enc_t2m_q): Encoder(
223
+ (enc): Sequential(
224
+ (0): ConvSC(
225
+ (conv): BasicConv2d(
226
+ (conv): Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
227
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
228
+ (act): SiLU()
229
+ )
230
+ )
231
+ (1): ConvSC(
232
+ (conv): BasicConv2d(
233
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
234
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
235
+ (act): SiLU()
236
+ )
237
+ )
238
+ (2): ConvSC(
239
+ (conv): BasicConv2d(
240
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
241
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
242
+ (act): SiLU()
243
+ )
244
+ )
245
+ (3): ConvSC(
246
+ (conv): BasicConv2d(
247
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
248
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
249
+ (act): SiLU()
250
+ )
251
+ )
252
+ )
253
+ )
254
+ (enc_t2m_k): Encoder(
255
+ (enc): Sequential(
256
+ (0): ConvSC(
257
+ (conv): BasicConv2d(
258
+ (conv): Conv2d(1, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
259
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
260
+ (act): SiLU()
261
+ )
262
+ )
263
+ (1): ConvSC(
264
+ (conv): BasicConv2d(
265
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
266
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
267
+ (act): SiLU()
268
+ )
269
+ )
270
+ (2): ConvSC(
271
+ (conv): BasicConv2d(
272
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
273
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
274
+ (act): SiLU()
275
+ )
276
+ )
277
+ (3): ConvSC(
278
+ (conv): BasicConv2d(
279
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
280
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
281
+ (act): SiLU()
282
+ )
283
+ )
284
+ )
285
+ )
286
+ (dec_u10_q): Decoder(
287
+ (dec): Sequential(
288
+ (0): ConvSC(
289
+ (conv): BasicConv2d(
290
+ (conv): Sequential(
291
+ (0): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
292
+ (1): PixelShuffle(upscale_factor=2)
293
+ )
294
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
295
+ (act): SiLU()
296
+ )
297
+ )
298
+ (1): ConvSC(
299
+ (conv): BasicConv2d(
300
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
301
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
302
+ (act): SiLU()
303
+ )
304
+ )
305
+ (2): ConvSC(
306
+ (conv): BasicConv2d(
307
+ (conv): Sequential(
308
+ (0): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
309
+ (1): PixelShuffle(upscale_factor=2)
310
+ )
311
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
312
+ (act): SiLU()
313
+ )
314
+ )
315
+ (3): ConvSC(
316
+ (conv): BasicConv2d(
317
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
318
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
319
+ (act): SiLU()
320
+ )
321
+ )
322
+ )
323
+ (readout): Conv2d(64, 1, kernel_size=(1, 1), stride=(1, 1))
324
+ )
325
+ (dec_u10_k): Decoder(
326
+ (dec): Sequential(
327
+ (0): ConvSC(
328
+ (conv): BasicConv2d(
329
+ (conv): Sequential(
330
+ (0): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
331
+ (1): PixelShuffle(upscale_factor=2)
332
+ )
333
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
334
+ (act): SiLU()
335
+ )
336
+ )
337
+ (1): ConvSC(
338
+ (conv): BasicConv2d(
339
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
340
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
341
+ (act): SiLU()
342
+ )
343
+ )
344
+ (2): ConvSC(
345
+ (conv): BasicConv2d(
346
+ (conv): Sequential(
347
+ (0): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
348
+ (1): PixelShuffle(upscale_factor=2)
349
+ )
350
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
351
+ (act): SiLU()
352
+ )
353
+ )
354
+ (3): ConvSC(
355
+ (conv): BasicConv2d(
356
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
357
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
358
+ (act): SiLU()
359
+ )
360
+ )
361
+ )
362
+ (readout): Conv2d(64, 1, kernel_size=(1, 1), stride=(1, 1))
363
+ )
364
+ (dec_v10_q): Decoder(
365
+ (dec): Sequential(
366
+ (0): ConvSC(
367
+ (conv): BasicConv2d(
368
+ (conv): Sequential(
369
+ (0): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
370
+ (1): PixelShuffle(upscale_factor=2)
371
+ )
372
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
373
+ (act): SiLU()
374
+ )
375
+ )
376
+ (1): ConvSC(
377
+ (conv): BasicConv2d(
378
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
379
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
380
+ (act): SiLU()
381
+ )
382
+ )
383
+ (2): ConvSC(
384
+ (conv): BasicConv2d(
385
+ (conv): Sequential(
386
+ (0): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
387
+ (1): PixelShuffle(upscale_factor=2)
388
+ )
389
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
390
+ (act): SiLU()
391
+ )
392
+ )
393
+ (3): ConvSC(
394
+ (conv): BasicConv2d(
395
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
396
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
397
+ (act): SiLU()
398
+ )
399
+ )
400
+ )
401
+ (readout): Conv2d(64, 1, kernel_size=(1, 1), stride=(1, 1))
402
+ )
403
+ (dec_v10_k): Decoder(
404
+ (dec): Sequential(
405
+ (0): ConvSC(
406
+ (conv): BasicConv2d(
407
+ (conv): Sequential(
408
+ (0): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
409
+ (1): PixelShuffle(upscale_factor=2)
410
+ )
411
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
412
+ (act): SiLU()
413
+ )
414
+ )
415
+ (1): ConvSC(
416
+ (conv): BasicConv2d(
417
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
418
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
419
+ (act): SiLU()
420
+ )
421
+ )
422
+ (2): ConvSC(
423
+ (conv): BasicConv2d(
424
+ (conv): Sequential(
425
+ (0): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
426
+ (1): PixelShuffle(upscale_factor=2)
427
+ )
428
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
429
+ (act): SiLU()
430
+ )
431
+ )
432
+ (3): ConvSC(
433
+ (conv): BasicConv2d(
434
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
435
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
436
+ (act): SiLU()
437
+ )
438
+ )
439
+ )
440
+ (readout): Conv2d(64, 1, kernel_size=(1, 1), stride=(1, 1))
441
+ )
442
+ (dec_t2m_q): Decoder(
443
+ (dec): Sequential(
444
+ (0): ConvSC(
445
+ (conv): BasicConv2d(
446
+ (conv): Sequential(
447
+ (0): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
448
+ (1): PixelShuffle(upscale_factor=2)
449
+ )
450
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
451
+ (act): SiLU()
452
+ )
453
+ )
454
+ (1): ConvSC(
455
+ (conv): BasicConv2d(
456
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
457
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
458
+ (act): SiLU()
459
+ )
460
+ )
461
+ (2): ConvSC(
462
+ (conv): BasicConv2d(
463
+ (conv): Sequential(
464
+ (0): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
465
+ (1): PixelShuffle(upscale_factor=2)
466
+ )
467
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
468
+ (act): SiLU()
469
+ )
470
+ )
471
+ (3): ConvSC(
472
+ (conv): BasicConv2d(
473
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
474
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
475
+ (act): SiLU()
476
+ )
477
+ )
478
+ )
479
+ (readout): Conv2d(64, 1, kernel_size=(1, 1), stride=(1, 1))
480
+ )
481
+ (dec_t2m_k): Decoder(
482
+ (dec): Sequential(
483
+ (0): ConvSC(
484
+ (conv): BasicConv2d(
485
+ (conv): Sequential(
486
+ (0): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
487
+ (1): PixelShuffle(upscale_factor=2)
488
+ )
489
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
490
+ (act): SiLU()
491
+ )
492
+ )
493
+ (1): ConvSC(
494
+ (conv): BasicConv2d(
495
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
496
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
497
+ (act): SiLU()
498
+ )
499
+ )
500
+ (2): ConvSC(
501
+ (conv): BasicConv2d(
502
+ (conv): Sequential(
503
+ (0): Conv2d(64, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
504
+ (1): PixelShuffle(upscale_factor=2)
505
+ )
506
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
507
+ (act): SiLU()
508
+ )
509
+ )
510
+ (3): ConvSC(
511
+ (conv): BasicConv2d(
512
+ (conv): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
513
+ (norm): GroupNorm(2, 64, eps=1e-05, affine=True)
514
+ (act): SiLU()
515
+ )
516
+ )
517
+ )
518
+ (readout): Conv2d(64, 1, kernel_size=(1, 1), stride=(1, 1))
519
+ )
520
+ (hid_q): CIMidNet(
521
+ (conv1): Conv2d(640, 512, kernel_size=(1, 1), stride=(1, 1))
522
+ (layers): ModuleList(
523
+ (0-7): 8 x CIAttBlock(
524
+ (norm_1): GroupNorm(1, 512, eps=1e-05, affine=True)
525
+ (norm_2): GroupNorm(1, 512, eps=1e-05, affine=True)
526
+ (attn_1): MultiHeadAttention_S(
527
+ (q_Conv): Sequential(
528
+ (0): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
529
+ (1): GroupNorm(1, 512, eps=1e-05, affine=True)
530
+ )
531
+ (v_Conv): Sequential(
532
+ (0): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
533
+ (1): GroupNorm(1, 512, eps=1e-05, affine=True)
534
+ )
535
+ (k_Conv): Sequential(
536
+ (0): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
537
+ (1): GroupNorm(1, 512, eps=1e-05, affine=True)
538
+ )
539
+ (v_post_f): Sequential(
540
+ (0): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
541
+ (1): GroupNorm(1, 512, eps=1e-05, affine=True)
542
+ (2): SiLU()
543
+ )
544
+ )
545
+ (ff): layerNormFeedForward(
546
+ (ff1): TAUSubBlock(
547
+ (norm1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
548
+ (attn): TemporalAttention(
549
+ (proj_1): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1))
550
+ (activation): GELU(approximate='none')
551
+ (spatial_gating_unit): TemporalAttentionModule(
552
+ (conv0): Conv2d(512, 512, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=512)
553
+ (conv_spatial): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(9, 9), dilation=(3, 3), groups=512)
554
+ (conv1): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1))
555
+ (avg_pool): AdaptiveAvgPool2d(output_size=1)
556
+ (fc): Sequential(
557
+ (0): Linear(in_features=512, out_features=16, bias=False)
558
+ (1): ReLU(inplace=True)
559
+ (2): Linear(in_features=16, out_features=512, bias=False)
560
+ (3): Sigmoid()
561
+ )
562
+ )
563
+ (proj_2): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1))
564
+ )
565
+ (drop_path): DropPath(drop_prob=0.100)
566
+ (norm2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
567
+ (mlp): MixMlp(
568
+ (fc1): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1))
569
+ (dwconv): DWConv(
570
+ (dwconv): Conv2d(2048, 2048, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=2048)
571
+ )
572
+ (act): GELU(approximate='none')
573
+ (fc2): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1))
574
+ (drop): Dropout(p=0.0, inplace=False)
575
+ )
576
+ )
577
+ )
578
+ )
579
+ )
580
+ (conv2): Conv2d(512, 640, kernel_size=(1, 1), stride=(1, 1))
581
+ )
582
+ (hid_k): CIMidNet(
583
+ (conv1): Conv2d(640, 512, kernel_size=(1, 1), stride=(1, 1))
584
+ (layers): ModuleList(
585
+ (0-7): 8 x CIAttBlock(
586
+ (norm_1): GroupNorm(1, 512, eps=1e-05, affine=True)
587
+ (norm_2): GroupNorm(1, 512, eps=1e-05, affine=True)
588
+ (attn_1): MultiHeadAttention_S(
589
+ (q_Conv): Sequential(
590
+ (0): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
591
+ (1): GroupNorm(1, 512, eps=1e-05, affine=True)
592
+ )
593
+ (v_Conv): Sequential(
594
+ (0): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
595
+ (1): GroupNorm(1, 512, eps=1e-05, affine=True)
596
+ )
597
+ (k_Conv): Sequential(
598
+ (0): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
599
+ (1): GroupNorm(1, 512, eps=1e-05, affine=True)
600
+ )
601
+ (v_post_f): Sequential(
602
+ (0): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
603
+ (1): GroupNorm(1, 512, eps=1e-05, affine=True)
604
+ (2): SiLU()
605
+ )
606
+ )
607
+ (ff): layerNormFeedForward(
608
+ (ff1): TAUSubBlock(
609
+ (norm1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
610
+ (attn): TemporalAttention(
611
+ (proj_1): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1))
612
+ (activation): GELU(approximate='none')
613
+ (spatial_gating_unit): TemporalAttentionModule(
614
+ (conv0): Conv2d(512, 512, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2), groups=512)
615
+ (conv_spatial): Conv2d(512, 512, kernel_size=(7, 7), stride=(1, 1), padding=(9, 9), dilation=(3, 3), groups=512)
616
+ (conv1): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1))
617
+ (avg_pool): AdaptiveAvgPool2d(output_size=1)
618
+ (fc): Sequential(
619
+ (0): Linear(in_features=512, out_features=16, bias=False)
620
+ (1): ReLU(inplace=True)
621
+ (2): Linear(in_features=16, out_features=512, bias=False)
622
+ (3): Sigmoid()
623
+ )
624
+ )
625
+ (proj_2): Conv2d(512, 512, kernel_size=(1, 1), stride=(1, 1))
626
+ )
627
+ (drop_path): DropPath(drop_prob=0.100)
628
+ (norm2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
629
+ (mlp): MixMlp(
630
+ (fc1): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1))
631
+ (dwconv): DWConv(
632
+ (dwconv): Conv2d(2048, 2048, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), groups=2048)
633
+ )
634
+ (act): GELU(approximate='none')
635
+ (fc2): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1))
636
+ (drop): Dropout(p=0.0, inplace=False)
637
+ )
638
+ )
639
+ )
640
+ )
641
+ )
642
+ (conv2): Conv2d(512, 640, kernel_size=(1, 1), stride=(1, 1))
643
+ )
644
+ )
645
+ | module | #parameters or shape | #flops |
646
+ |:-----------------------------|:-----------------------|:-----------|
647
+ | model | 68.544M | 81.216G |
648
+ | enc_u10_q.enc | 0.112M | 0.893G |
649
+ | enc_u10_q.enc.0.conv | 0.768K | 36.7M |
650
+ | enc_u10_q.enc.0.conv.conv | 0.64K | 23.593M |
651
+ | enc_u10_q.enc.0.conv.norm | 0.128K | 13.107M |
652
+ | enc_u10_q.enc.1.conv | 37.056K | 0.381G |
653
+ | enc_u10_q.enc.1.conv.conv | 36.928K | 0.377G |
654
+ | enc_u10_q.enc.1.conv.norm | 0.128K | 3.277M |
655
+ | enc_u10_q.enc.2.conv | 37.056K | 0.381G |
656
+ | enc_u10_q.enc.2.conv.conv | 36.928K | 0.377G |
657
+ | enc_u10_q.enc.2.conv.norm | 0.128K | 3.277M |
658
+ | enc_u10_q.enc.3.conv | 37.056K | 95.191M |
659
+ | enc_u10_q.enc.3.conv.conv | 36.928K | 94.372M |
660
+ | enc_u10_q.enc.3.conv.norm | 0.128K | 0.819M |
661
+ | enc_u10_k.enc | 0.112M | 1.787G |
662
+ | enc_u10_k.enc.0.conv | 0.768K | 73.4M |
663
+ | enc_u10_k.enc.0.conv.conv | 0.64K | 47.186M |
664
+ | enc_u10_k.enc.0.conv.norm | 0.128K | 26.214M |
665
+ | enc_u10_k.enc.1.conv | 37.056K | 0.762G |
666
+ | enc_u10_k.enc.1.conv.conv | 36.928K | 0.755G |
667
+ | enc_u10_k.enc.1.conv.norm | 0.128K | 6.554M |
668
+ | enc_u10_k.enc.2.conv | 37.056K | 0.762G |
669
+ | enc_u10_k.enc.2.conv.conv | 36.928K | 0.755G |
670
+ | enc_u10_k.enc.2.conv.norm | 0.128K | 6.554M |
671
+ | enc_u10_k.enc.3.conv | 37.056K | 0.19G |
672
+ | enc_u10_k.enc.3.conv.conv | 36.928K | 0.189G |
673
+ | enc_u10_k.enc.3.conv.norm | 0.128K | 1.638M |
674
+ | enc_v10_q.enc | 0.112M | 0.893G |
675
+ | enc_v10_q.enc.0.conv | 0.768K | 36.7M |
676
+ | enc_v10_q.enc.0.conv.conv | 0.64K | 23.593M |
677
+ | enc_v10_q.enc.0.conv.norm | 0.128K | 13.107M |
678
+ | enc_v10_q.enc.1.conv | 37.056K | 0.381G |
679
+ | enc_v10_q.enc.1.conv.conv | 36.928K | 0.377G |
680
+ | enc_v10_q.enc.1.conv.norm | 0.128K | 3.277M |
681
+ | enc_v10_q.enc.2.conv | 37.056K | 0.381G |
682
+ | enc_v10_q.enc.2.conv.conv | 36.928K | 0.377G |
683
+ | enc_v10_q.enc.2.conv.norm | 0.128K | 3.277M |
684
+ | enc_v10_q.enc.3.conv | 37.056K | 95.191M |
685
+ | enc_v10_q.enc.3.conv.conv | 36.928K | 94.372M |
686
+ | enc_v10_q.enc.3.conv.norm | 0.128K | 0.819M |
687
+ | enc_v10_k.enc | 0.112M | 1.787G |
688
+ | enc_v10_k.enc.0.conv | 0.768K | 73.4M |
689
+ | enc_v10_k.enc.0.conv.conv | 0.64K | 47.186M |
690
+ | enc_v10_k.enc.0.conv.norm | 0.128K | 26.214M |
691
+ | enc_v10_k.enc.1.conv | 37.056K | 0.762G |
692
+ | enc_v10_k.enc.1.conv.conv | 36.928K | 0.755G |
693
+ | enc_v10_k.enc.1.conv.norm | 0.128K | 6.554M |
694
+ | enc_v10_k.enc.2.conv | 37.056K | 0.762G |
695
+ | enc_v10_k.enc.2.conv.conv | 36.928K | 0.755G |
696
+ | enc_v10_k.enc.2.conv.norm | 0.128K | 6.554M |
697
+ | enc_v10_k.enc.3.conv | 37.056K | 0.19G |
698
+ | enc_v10_k.enc.3.conv.conv | 36.928K | 0.189G |
699
+ | enc_v10_k.enc.3.conv.norm | 0.128K | 1.638M |
700
+ | enc_t2m_q.enc | 0.112M | 0.893G |
701
+ | enc_t2m_q.enc.0.conv | 0.768K | 36.7M |
702
+ | enc_t2m_q.enc.0.conv.conv | 0.64K | 23.593M |
703
+ | enc_t2m_q.enc.0.conv.norm | 0.128K | 13.107M |
704
+ | enc_t2m_q.enc.1.conv | 37.056K | 0.381G |
705
+ | enc_t2m_q.enc.1.conv.conv | 36.928K | 0.377G |
706
+ | enc_t2m_q.enc.1.conv.norm | 0.128K | 3.277M |
707
+ | enc_t2m_q.enc.2.conv | 37.056K | 0.381G |
708
+ | enc_t2m_q.enc.2.conv.conv | 36.928K | 0.377G |
709
+ | enc_t2m_q.enc.2.conv.norm | 0.128K | 3.277M |
710
+ | enc_t2m_q.enc.3.conv | 37.056K | 95.191M |
711
+ | enc_t2m_q.enc.3.conv.conv | 36.928K | 94.372M |
712
+ | enc_t2m_q.enc.3.conv.norm | 0.128K | 0.819M |
713
+ | enc_t2m_k.enc | 0.112M | 1.787G |
714
+ | enc_t2m_k.enc.0.conv | 0.768K | 73.4M |
715
+ | enc_t2m_k.enc.0.conv.conv | 0.64K | 47.186M |
716
+ | enc_t2m_k.enc.0.conv.norm | 0.128K | 26.214M |
717
+ | enc_t2m_k.enc.1.conv | 37.056K | 0.762G |
718
+ | enc_t2m_k.enc.1.conv.conv | 36.928K | 0.755G |
719
+ | enc_t2m_k.enc.1.conv.norm | 0.128K | 6.554M |
720
+ | enc_t2m_k.enc.2.conv | 37.056K | 0.762G |
721
+ | enc_t2m_k.enc.2.conv.conv | 36.928K | 0.755G |
722
+ | enc_t2m_k.enc.2.conv.norm | 0.128K | 6.554M |
723
+ | enc_t2m_k.enc.3.conv | 37.056K | 0.19G |
724
+ | enc_t2m_k.enc.3.conv.conv | 36.928K | 0.189G |
725
+ | enc_t2m_k.enc.3.conv.norm | 0.128K | 1.638M |
726
+ | dec_u10_q | 0.37M | 3.81G |
727
+ | dec_u10_q.dec | 0.37M | 3.808G |
728
+ | dec_u10_q.dec.0.conv | 0.148M | 0.381G |
729
+ | dec_u10_q.dec.1.conv | 37.056K | 0.381G |
730
+ | dec_u10_q.dec.2.conv | 0.148M | 1.523G |
731
+ | dec_u10_q.dec.3.conv | 37.056K | 1.523G |
732
+ | dec_u10_q.readout | 65 | 2.621M |
733
+ | dec_u10_q.readout.weight | (1, 64, 1, 1) | |
734
+ | dec_u10_q.readout.bias | (1,) | |
735
+ | dec_u10_k | 0.37M | 3.81G |
736
+ | dec_u10_k.dec | 0.37M | 3.808G |
737
+ | dec_u10_k.dec.0.conv | 0.148M | 0.381G |
738
+ | dec_u10_k.dec.1.conv | 37.056K | 0.381G |
739
+ | dec_u10_k.dec.2.conv | 0.148M | 1.523G |
740
+ | dec_u10_k.dec.3.conv | 37.056K | 1.523G |
741
+ | dec_u10_k.readout | 65 | 2.621M |
742
+ | dec_u10_k.readout.weight | (1, 64, 1, 1) | |
743
+ | dec_u10_k.readout.bias | (1,) | |
744
+ | dec_v10_q | 0.37M | 3.81G |
745
+ | dec_v10_q.dec | 0.37M | 3.808G |
746
+ | dec_v10_q.dec.0.conv | 0.148M | 0.381G |
747
+ | dec_v10_q.dec.1.conv | 37.056K | 0.381G |
748
+ | dec_v10_q.dec.2.conv | 0.148M | 1.523G |
749
+ | dec_v10_q.dec.3.conv | 37.056K | 1.523G |
750
+ | dec_v10_q.readout | 65 | 2.621M |
751
+ | dec_v10_q.readout.weight | (1, 64, 1, 1) | |
752
+ | dec_v10_q.readout.bias | (1,) | |
753
+ | dec_v10_k | 0.37M | 3.81G |
754
+ | dec_v10_k.dec | 0.37M | 3.808G |
755
+ | dec_v10_k.dec.0.conv | 0.148M | 0.381G |
756
+ | dec_v10_k.dec.1.conv | 37.056K | 0.381G |
757
+ | dec_v10_k.dec.2.conv | 0.148M | 1.523G |
758
+ | dec_v10_k.dec.3.conv | 37.056K | 1.523G |
759
+ | dec_v10_k.readout | 65 | 2.621M |
760
+ | dec_v10_k.readout.weight | (1, 64, 1, 1) | |
761
+ | dec_v10_k.readout.bias | (1,) | |
762
+ | dec_t2m_q | 0.37M | 3.81G |
763
+ | dec_t2m_q.dec | 0.37M | 3.808G |
764
+ | dec_t2m_q.dec.0.conv | 0.148M | 0.381G |
765
+ | dec_t2m_q.dec.1.conv | 37.056K | 0.381G |
766
+ | dec_t2m_q.dec.2.conv | 0.148M | 1.523G |
767
+ | dec_t2m_q.dec.3.conv | 37.056K | 1.523G |
768
+ | dec_t2m_q.readout | 65 | 2.621M |
769
+ | dec_t2m_q.readout.weight | (1, 64, 1, 1) | |
770
+ | dec_t2m_q.readout.bias | (1,) | |
771
+ | dec_t2m_k | 0.37M | 3.81G |
772
+ | dec_t2m_k.dec | 0.37M | 3.808G |
773
+ | dec_t2m_k.dec.0.conv | 0.148M | 0.381G |
774
+ | dec_t2m_k.dec.1.conv | 37.056K | 0.381G |
775
+ | dec_t2m_k.dec.2.conv | 0.148M | 1.523G |
776
+ | dec_t2m_k.dec.3.conv | 37.056K | 1.523G |
777
+ | dec_t2m_k.readout | 65 | 2.621M |
778
+ | dec_t2m_k.readout.weight | (1, 64, 1, 1) | |
779
+ | dec_t2m_k.readout.bias | (1,) | |
780
+ | hid_q | 32.826M | 25.157G |
781
+ | hid_q.conv1 | 0.328M | 0.252G |
782
+ | hid_q.conv1.weight | (512, 640, 1, 1) | |
783
+ | hid_q.conv1.bias | (512,) | |
784
+ | hid_q.layers | 32.17M | 24.653G |
785
+ | hid_q.layers.0 | 4.021M | 3.082G |
786
+ | hid_q.layers.1 | 4.021M | 3.082G |
787
+ | hid_q.layers.2 | 4.021M | 3.082G |
788
+ | hid_q.layers.3 | 4.021M | 3.082G |
789
+ | hid_q.layers.4 | 4.021M | 3.082G |
790
+ | hid_q.layers.5 | 4.021M | 3.082G |
791
+ | hid_q.layers.6 | 4.021M | 3.082G |
792
+ | hid_q.layers.7 | 4.021M | 3.082G |
793
+ | hid_q.conv2 | 0.328M | 0.252G |
794
+ | hid_q.conv2.weight | (640, 512, 1, 1) | |
795
+ | hid_q.conv2.bias | (640,) | |
796
+ | hid_k | 32.826M | 25.157G |
797
+ | hid_k.conv1 | 0.328M | 0.252G |
798
+ | hid_k.conv1.weight | (512, 640, 1, 1) | |
799
+ | hid_k.conv1.bias | (512,) | |
800
+ | hid_k.layers | 32.17M | 24.653G |
801
+ | hid_k.layers.0 | 4.021M | 3.082G |
802
+ | hid_k.layers.1 | 4.021M | 3.082G |
803
+ | hid_k.layers.2 | 4.021M | 3.082G |
804
+ | hid_k.layers.3 | 4.021M | 3.082G |
805
+ | hid_k.layers.4 | 4.021M | 3.082G |
806
+ | hid_k.layers.5 | 4.021M | 3.082G |
807
+ | hid_k.layers.6 | 4.021M | 3.082G |
808
+ | hid_k.layers.7 | 4.021M | 3.082G |
809
+ | hid_k.conv2 | 0.328M | 0.252G |
810
+ | hid_k.conv2.weight | (640, 512, 1, 1) | |
811
+ | hid_k.conv2.bias | (640,) | |
812
+ --------------------------------------------------------------------------------
813
+
814
+ 2024-11-12 17:46:07,210 - w1 : 1.9824299466392266 | w2 : 0.0597038581172535 | w3 : 0.019894629905273076
815
+ 2024-11-12 17:51:23,077 - Epoch 1: Lr: 0.0009999 | Train Loss: 0.2179366 | Vali Loss: 0.1064958 | Rec Loss: 0.0320693 | Latent Loss: 0.0744265 | Pre Loss: 0.0315628
816
+ 2024-11-12 17:56:44,748 - Epoch 2: Lr: 0.0009998 | Train Loss: 0.1413911 | Vali Loss: 0.0917718 | Rec Loss: 0.0292384 | Latent Loss: 0.0625334 | Pre Loss: 0.0286205
817
+ 2024-11-12 18:02:09,913 - Epoch 3: Lr: 0.0009994 | Train Loss: 0.1062470 | Vali Loss: 0.0842272 | Rec Loss: 0.0276109 | Latent Loss: 0.0566162 | Pre Loss: 0.0264605
818
+ 2024-11-12 18:07:37,650 - Epoch 4: Lr: 0.0009990 | Train Loss: 0.0896681 | Vali Loss: 0.0787217 | Rec Loss: 0.0255277 | Latent Loss: 0.0531941 | Pre Loss: 0.0256292
819
+ 2024-11-12 18:13:08,627 - Epoch 5: Lr: 0.0009985 | Train Loss: 0.0795521 | Vali Loss: 0.0679551 | Rec Loss: 0.0245178 | Latent Loss: 0.0434373 | Pre Loss: 0.0244314
820
+ 2024-11-12 18:18:43,025 - Epoch 6: Lr: 0.0009978 | Train Loss: 0.0748503 | Vali Loss: 0.0698862 | Rec Loss: 0.0245942 | Latent Loss: 0.0452921 | Pre Loss: 0.0237178
821
+ 2024-11-12 18:24:19,472 - Epoch 7: Lr: 0.0009970 | Train Loss: 0.0757530 | Vali Loss: 0.0639117 | Rec Loss: 0.0243705 | Latent Loss: 0.0395411 | Pre Loss: 0.0227817
822
+ 2024-11-12 18:29:59,312 - Epoch 8: Lr: 0.0009961 | Train Loss: 0.0726289 | Vali Loss: 0.0664225 | Rec Loss: 0.0229928 | Latent Loss: 0.0434297 | Pre Loss: 0.0227751
823
+ 2024-11-12 18:35:40,513 - Epoch 9: Lr: 0.0009950 | Train Loss: 0.0698427 | Vali Loss: 0.0611381 | Rec Loss: 0.0229339 | Latent Loss: 0.0382042 | Pre Loss: 0.0221360
824
+ 2024-11-12 18:41:26,524 - Epoch 10: Lr: 0.0009939 | Train Loss: 0.0708630 | Vali Loss: 0.0616351 | Rec Loss: 0.0226371 | Latent Loss: 0.0389980 | Pre Loss: 0.0215934
825
+ 2024-11-12 18:47:15,391 - Epoch 11: Lr: 0.0009926 | Train Loss: 0.0651742 | Vali Loss: 0.0561315 | Rec Loss: 0.0221701 | Latent Loss: 0.0339614 | Pre Loss: 0.0208683
826
+ 2024-11-12 18:53:07,905 - Epoch 12: Lr: 0.0009912 | Train Loss: 0.0612987 | Vali Loss: 0.0529133 | Rec Loss: 0.0215742 | Latent Loss: 0.0313392 | Pre Loss: 0.0202986
827
+ 2024-11-12 18:59:04,048 - Epoch 13: Lr: 0.0009896 | Train Loss: 0.0582426 | Vali Loss: 0.0523291 | Rec Loss: 0.0207016 | Latent Loss: 0.0316275 | Pre Loss: 0.0201663
828
+ 2024-11-12 19:05:03,539 - Epoch 14: Lr: 0.0009880 | Train Loss: 0.0584667 | Vali Loss: 0.0519960 | Rec Loss: 0.0207176 | Latent Loss: 0.0312784 | Pre Loss: 0.0201933
829
+ 2024-11-12 19:11:06,157 - Epoch 15: Lr: 0.0009862 | Train Loss: 0.0578432 | Vali Loss: 0.0532566 | Rec Loss: 0.0206760 | Latent Loss: 0.0325806 | Pre Loss: 0.0198487
830
+ 2024-11-12 19:17:10,456 - Epoch 16: Lr: 0.0009843 | Train Loss: 0.0574470 | Vali Loss: 0.0530245 | Rec Loss: 0.0201388 | Latent Loss: 0.0328857 | Pre Loss: 0.0196058
831
+ 2024-11-12 19:23:17,694 - Epoch 17: Lr: 0.0009823 | Train Loss: 0.0563114 | Vali Loss: 0.0509097 | Rec Loss: 0.0199237 | Latent Loss: 0.0309860 | Pre Loss: 0.0197462
832
+ 2024-11-12 19:29:30,767 - Epoch 18: Lr: 0.0009802 | Train Loss: 0.0560896 | Vali Loss: 0.0511374 | Rec Loss: 0.0198565 | Latent Loss: 0.0312810 | Pre Loss: 0.0197640
833
+ 2024-11-12 19:35:45,334 - Epoch 19: Lr: 0.0009779 | Train Loss: 0.0554596 | Vali Loss: 0.0482234 | Rec Loss: 0.0189860 | Latent Loss: 0.0292374 | Pre Loss: 0.0185189
834
+ 2024-11-12 19:42:05,597 - Epoch 20: Lr: 0.0009756 | Train Loss: 0.0531250 | Vali Loss: 0.0507526 | Rec Loss: 0.0190520 | Latent Loss: 0.0317007 | Pre Loss: 0.0183090
835
+ 2024-11-12 19:48:27,586 - Epoch 21: Lr: 0.0009731 | Train Loss: 0.0526246 | Vali Loss: 0.0456903 | Rec Loss: 0.0185719 | Latent Loss: 0.0271184 | Pre Loss: 0.0180610
836
+ 2024-11-12 19:54:53,716 - Epoch 22: Lr: 0.0009705 | Train Loss: 0.0532047 | Vali Loss: 0.0478828 | Rec Loss: 0.0184654 | Latent Loss: 0.0294174 | Pre Loss: 0.0180788
837
+ 2024-11-12 20:01:21,752 - Epoch 23: Lr: 0.0009678 | Train Loss: 0.0516321 | Vali Loss: 0.0466723 | Rec Loss: 0.0183587 | Latent Loss: 0.0283136 | Pre Loss: 0.0179209
838
+ 2024-11-12 20:07:53,136 - Epoch 24: Lr: 0.0009649 | Train Loss: 0.0506253 | Vali Loss: 0.0483531 | Rec Loss: 0.0180644 | Latent Loss: 0.0302887 | Pre Loss: 0.0172811
839
+ 2024-11-12 20:14:29,805 - Epoch 25: Lr: 0.0009620 | Train Loss: 0.0514809 | Vali Loss: 0.0474071 | Rec Loss: 0.0179728 | Latent Loss: 0.0294343 | Pre Loss: 0.0175392
840
+ 2024-11-12 20:21:08,070 - Epoch 26: Lr: 0.0009589 | Train Loss: 0.0501679 | Vali Loss: 0.0479947 | Rec Loss: 0.0175719 | Latent Loss: 0.0304228 | Pre Loss: 0.0170769
841
+ 2024-11-12 20:27:51,494 - Epoch 27: Lr: 0.0009557 | Train Loss: 0.0515359 | Vali Loss: 0.0474806 | Rec Loss: 0.0176195 | Latent Loss: 0.0298611 | Pre Loss: 0.0173007
842
+ 2024-11-12 20:34:38,141 - Epoch 28: Lr: 0.0009525 | Train Loss: 0.0507013 | Vali Loss: 0.0457178 | Rec Loss: 0.0172503 | Latent Loss: 0.0284675 | Pre Loss: 0.0168624
843
+ 2024-11-12 20:41:27,514 - Epoch 29: Lr: 0.0009491 | Train Loss: 0.0486515 | Vali Loss: 0.0479886 | Rec Loss: 0.0175811 | Latent Loss: 0.0304075 | Pre Loss: 0.0175120
844
+ 2024-11-12 20:48:19,193 - Epoch 30: Lr: 0.0009456 | Train Loss: 0.0492980 | Vali Loss: 0.0478889 | Rec Loss: 0.0173638 | Latent Loss: 0.0305251 | Pre Loss: 0.0170756
845
+ 2024-11-12 20:55:16,375 - Epoch 31: Lr: 0.0009419 | Train Loss: 0.0491991 | Vali Loss: 0.0501551 | Rec Loss: 0.0173867 | Latent Loss: 0.0327684 | Pre Loss: 0.0172594
846
+ 2024-11-12 21:02:16,833 - Epoch 32: Lr: 0.0009382 | Train Loss: 0.0493678 | Vali Loss: 0.0454871 | Rec Loss: 0.0168090 | Latent Loss: 0.0286781 | Pre Loss: 0.0164255
847
+ 2024-11-12 21:09:21,703 - Epoch 33: Lr: 0.0009344 | Train Loss: 0.0499863 | Vali Loss: 0.0492082 | Rec Loss: 0.0169317 | Latent Loss: 0.0322765 | Pre Loss: 0.0167634
848
+ 2024-11-12 21:16:29,268 - Epoch 34: Lr: 0.0009304 | Train Loss: 0.0493426 | Vali Loss: 0.0481798 | Rec Loss: 0.0166075 | Latent Loss: 0.0315724 | Pre Loss: 0.0161976
849
+ 2024-11-12 21:23:41,579 - Epoch 35: Lr: 0.0009264 | Train Loss: 0.0485375 | Vali Loss: 0.0469319 | Rec Loss: 0.0163999 | Latent Loss: 0.0305320 | Pre Loss: 0.0159891
850
+ 2024-11-12 21:30:56,947 - Epoch 36: Lr: 0.0009222 | Train Loss: 0.0481543 | Vali Loss: 0.0462840 | Rec Loss: 0.0165936 | Latent Loss: 0.0296904 | Pre Loss: 0.0160774
851
+ 2024-11-12 21:38:15,355 - Epoch 37: Lr: 0.0009180 | Train Loss: 0.0476893 | Vali Loss: 0.0459986 | Rec Loss: 0.0166430 | Latent Loss: 0.0293556 | Pre Loss: 0.0163926
852
+ 2024-11-12 21:45:37,217 - Epoch 38: Lr: 0.0009136 | Train Loss: 0.0466059 | Vali Loss: 0.0437210 | Rec Loss: 0.0158623 | Latent Loss: 0.0278587 | Pre Loss: 0.0154103
853
+ 2024-11-12 21:53:04,370 - Epoch 39: Lr: 0.0009092 | Train Loss: 0.0464931 | Vali Loss: 0.0439378 | Rec Loss: 0.0160861 | Latent Loss: 0.0278518 | Pre Loss: 0.0157589
854
+ 2024-11-12 22:00:32,935 - Epoch 40: Lr: 0.0009046 | Train Loss: 0.0447973 | Vali Loss: 0.0464864 | Rec Loss: 0.0165211 | Latent Loss: 0.0299653 | Pre Loss: 0.0164638
855
+ 2024-11-12 22:08:05,966 - Epoch 41: Lr: 0.0008999 | Train Loss: 0.0448013 | Vali Loss: 0.0440178 | Rec Loss: 0.0159846 | Latent Loss: 0.0280332 | Pre Loss: 0.0157454
856
+ 2024-11-12 22:15:41,024 - Epoch 42: Lr: 0.0008952 | Train Loss: 0.0446265 | Vali Loss: 0.0434645 | Rec Loss: 0.0158746 | Latent Loss: 0.0275899 | Pre Loss: 0.0156275
857
+ 2024-11-12 22:23:23,500 - Epoch 43: Lr: 0.0008903 | Train Loss: 0.0436073 | Vali Loss: 0.0423922 | Rec Loss: 0.0156740 | Latent Loss: 0.0267182 | Pre Loss: 0.0152447
858
+ 2024-11-12 22:31:06,596 - Epoch 44: Lr: 0.0008854 | Train Loss: 0.0427057 | Vali Loss: 0.0420294 | Rec Loss: 0.0157603 | Latent Loss: 0.0262691 | Pre Loss: 0.0154664
859
+ 2024-11-12 22:38:53,720 - Epoch 45: Lr: 0.0008803 | Train Loss: 0.0420013 | Vali Loss: 0.0409309 | Rec Loss: 0.0156275 | Latent Loss: 0.0253034 | Pre Loss: 0.0153511
860
+ 2024-11-12 22:46:45,158 - Epoch 46: Lr: 0.0008752 | Train Loss: 0.0418653 | Vali Loss: 0.0408055 | Rec Loss: 0.0159289 | Latent Loss: 0.0248766 | Pre Loss: 0.0157681
861
+ 2024-11-12 22:54:39,705 - Epoch 47: Lr: 0.0008699 | Train Loss: 0.0411758 | Vali Loss: 0.0401105 | Rec Loss: 0.0156248 | Latent Loss: 0.0244857 | Pre Loss: 0.0152882
862
+ 2024-11-12 23:02:38,939 - Epoch 48: Lr: 0.0008646 | Train Loss: 0.0402309 | Vali Loss: 0.0400719 | Rec Loss: 0.0155923 | Latent Loss: 0.0244796 | Pre Loss: 0.0152030
863
+ 2024-11-12 23:10:39,694 - Epoch 49: Lr: 0.0008592 | Train Loss: 0.0404111 | Vali Loss: 0.0405820 | Rec Loss: 0.0159969 | Latent Loss: 0.0245851 | Pre Loss: 0.0156107
864
+ 2024-11-12 23:18:41,263 - Epoch 50: Lr: 0.0008537 | Train Loss: 0.0393008 | Vali Loss: 0.0394572 | Rec Loss: 0.0156420 | Latent Loss: 0.0238152 | Pre Loss: 0.0154284
865
+ 2024-11-12 23:26:48,308 - Epoch 51: Lr: 0.0008481 | Train Loss: 0.0389817 | Vali Loss: 0.0407820 | Rec Loss: 0.0152802 | Latent Loss: 0.0255019 | Pre Loss: 0.0147308
866
+ 2024-11-12 23:34:57,401 - Epoch 52: Lr: 0.0008424 | Train Loss: 0.0405326 | Vali Loss: 0.0401196 | Rec Loss: 0.0153136 | Latent Loss: 0.0248060 | Pre Loss: 0.0152191
867
+ 2024-11-12 23:43:08,016 - Epoch 53: Lr: 0.0008367 | Train Loss: 0.0399418 | Vali Loss: 0.0390719 | Rec Loss: 0.0153355 | Latent Loss: 0.0237365 | Pre Loss: 0.0150080
868
+ 2024-11-12 23:51:24,829 - Epoch 54: Lr: 0.0008308 | Train Loss: 0.0385613 | Vali Loss: 0.0386345 | Rec Loss: 0.0152658 | Latent Loss: 0.0233687 | Pre Loss: 0.0149651
869
+ 2024-11-12 23:59:47,385 - Epoch 55: Lr: 0.0008249 | Train Loss: 0.0389355 | Vali Loss: 0.0380017 | Rec Loss: 0.0151223 | Latent Loss: 0.0228793 | Pre Loss: 0.0147387
870
+ 2024-11-13 00:08:11,503 - Epoch 56: Lr: 0.0008189 | Train Loss: 0.0388482 | Vali Loss: 0.0375697 | Rec Loss: 0.0150351 | Latent Loss: 0.0225346 | Pre Loss: 0.0144703
871
+ 2024-11-13 00:16:38,028 - Epoch 57: Lr: 0.0008128 | Train Loss: 0.0383744 | Vali Loss: 0.0375771 | Rec Loss: 0.0147132 | Latent Loss: 0.0228640 | Pre Loss: 0.0142515
872
+ 2024-11-13 00:25:07,060 - Epoch 58: Lr: 0.0008066 | Train Loss: 0.0376353 | Vali Loss: 0.0380641 | Rec Loss: 0.0148954 | Latent Loss: 0.0231687 | Pre Loss: 0.0145569
873
+ 2024-11-13 00:33:40,224 - Epoch 59: Lr: 0.0008004 | Train Loss: 0.0376926 | Vali Loss: 0.0375467 | Rec Loss: 0.0146381 | Latent Loss: 0.0229086 | Pre Loss: 0.0143016
874
+ 2024-11-13 00:42:18,134 - Epoch 60: Lr: 0.0007941 | Train Loss: 0.0376747 | Vali Loss: 0.0372038 | Rec Loss: 0.0147100 | Latent Loss: 0.0224938 | Pre Loss: 0.0142889
875
+ 2024-11-13 00:50:57,276 - Epoch 61: Lr: 0.0007877 | Train Loss: 0.0374373 | Vali Loss: 0.0390231 | Rec Loss: 0.0147411 | Latent Loss: 0.0242820 | Pre Loss: 0.0144308
876
+ 2024-11-13 00:59:39,044 - Epoch 62: Lr: 0.0007813 | Train Loss: 0.0376981 | Vali Loss: 0.0401980 | Rec Loss: 0.0150912 | Latent Loss: 0.0251068 | Pre Loss: 0.0148102
877
+ 2024-11-13 01:08:25,900 - Epoch 63: Lr: 0.0007747 | Train Loss: 0.0387563 | Vali Loss: 0.0381311 | Rec Loss: 0.0146184 | Latent Loss: 0.0235128 | Pre Loss: 0.0141077
878
+ 2024-11-13 01:17:15,251 - Epoch 64: Lr: 0.0007681 | Train Loss: 0.0385607 | Vali Loss: 0.0382080 | Rec Loss: 0.0143749 | Latent Loss: 0.0238330 | Pre Loss: 0.0139498
879
+ 2024-11-13 01:26:08,122 - Epoch 65: Lr: 0.0007615 | Train Loss: 0.0385769 | Vali Loss: 0.0381712 | Rec Loss: 0.0144931 | Latent Loss: 0.0236781 | Pre Loss: 0.0140193
880
+ 2024-11-13 01:35:01,356 - Epoch 66: Lr: 0.0007548 | Train Loss: 0.0386126 | Vali Loss: 0.0377264 | Rec Loss: 0.0143659 | Latent Loss: 0.0233604 | Pre Loss: 0.0140580
881
+ 2024-11-13 01:44:01,803 - Epoch 67: Lr: 0.0007480 | Train Loss: 0.0375147 | Vali Loss: 0.0371596 | Rec Loss: 0.0143094 | Latent Loss: 0.0228502 | Pre Loss: 0.0137981
882
+ 2024-11-13 01:53:05,516 - Epoch 68: Lr: 0.0007411 | Train Loss: 0.0376426 | Vali Loss: 0.0371402 | Rec Loss: 0.0144182 | Latent Loss: 0.0227220 | Pre Loss: 0.0140126
883
+ 2024-11-13 02:02:12,135 - Epoch 69: Lr: 0.0007342 | Train Loss: 0.0372720 | Vali Loss: 0.0400003 | Rec Loss: 0.0145452 | Latent Loss: 0.0254551 | Pre Loss: 0.0143594
884
+ 2024-11-13 02:11:20,666 - Epoch 70: Lr: 0.0007273 | Train Loss: 0.0370756 | Vali Loss: 0.0371792 | Rec Loss: 0.0141913 | Latent Loss: 0.0229880 | Pre Loss: 0.0137052
885
+ 2024-11-13 02:20:33,453 - Epoch 71: Lr: 0.0007202 | Train Loss: 0.0373651 | Vali Loss: 0.0375881 | Rec Loss: 0.0142808 | Latent Loss: 0.0233073 | Pre Loss: 0.0139151
886
+ 2024-11-13 02:29:50,543 - Epoch 72: Lr: 0.0007132 | Train Loss: 0.0373200 | Vali Loss: 0.0367737 | Rec Loss: 0.0140907 | Latent Loss: 0.0226830 | Pre Loss: 0.0136385
887
+ 2024-11-13 02:39:11,176 - Epoch 73: Lr: 0.0007061 | Train Loss: 0.0373588 | Vali Loss: 0.0369920 | Rec Loss: 0.0142136 | Latent Loss: 0.0227784 | Pre Loss: 0.0139104
888
+ 2024-11-13 02:48:32,492 - Epoch 74: Lr: 0.0006989 | Train Loss: 0.0367414 | Vali Loss: 0.0358157 | Rec Loss: 0.0140157 | Latent Loss: 0.0218001 | Pre Loss: 0.0136418
889
+ 2024-11-13 02:58:00,121 - Epoch 75: Lr: 0.0006917 | Train Loss: 0.0354856 | Vali Loss: 0.0362462 | Rec Loss: 0.0140268 | Latent Loss: 0.0222194 | Pre Loss: 0.0135061
890
+ 2024-11-13 03:07:30,364 - Epoch 76: Lr: 0.0006844 | Train Loss: 0.0355047 | Vali Loss: 0.0360007 | Rec Loss: 0.0138197 | Latent Loss: 0.0221810 | Pre Loss: 0.0134047
891
+ 2024-11-13 03:17:00,728 - Epoch 77: Lr: 0.0006771 | Train Loss: 0.0354140 | Vali Loss: 0.0361308 | Rec Loss: 0.0138303 | Latent Loss: 0.0223005 | Pre Loss: 0.0134271
892
+ 2024-11-13 03:26:35,263 - Epoch 78: Lr: 0.0006697 | Train Loss: 0.0362230 | Vali Loss: 0.0369964 | Rec Loss: 0.0138454 | Latent Loss: 0.0231510 | Pre Loss: 0.0134351
893
+ 2024-11-13 03:36:13,076 - Epoch 79: Lr: 0.0006623 | Train Loss: 0.0364093 | Vali Loss: 0.0373455 | Rec Loss: 0.0139383 | Latent Loss: 0.0234071 | Pre Loss: 0.0135482
894
+ 2024-11-13 03:45:55,275 - Epoch 80: Lr: 0.0006549 | Train Loss: 0.0368220 | Vali Loss: 0.0373895 | Rec Loss: 0.0139846 | Latent Loss: 0.0234049 | Pre Loss: 0.0136771
895
+ 2024-11-13 03:55:38,620 - Epoch 81: Lr: 0.0006474 | Train Loss: 0.0369614 | Vali Loss: 0.0379454 | Rec Loss: 0.0139437 | Latent Loss: 0.0240017 | Pre Loss: 0.0134442
896
+ 2024-11-13 04:05:26,040 - Epoch 82: Lr: 0.0006399 | Train Loss: 0.0366337 | Vali Loss: 0.0366650 | Rec Loss: 0.0138344 | Latent Loss: 0.0228306 | Pre Loss: 0.0133879
897
+ 2024-11-13 04:15:19,545 - Epoch 83: Lr: 0.0006323 | Train Loss: 0.0364320 | Vali Loss: 0.0359162 | Rec Loss: 0.0137965 | Latent Loss: 0.0221197 | Pre Loss: 0.0132712
898
+ 2024-11-13 04:25:13,807 - Epoch 84: Lr: 0.0006247 | Train Loss: 0.0358261 | Vali Loss: 0.0388882 | Rec Loss: 0.0138466 | Latent Loss: 0.0250416 | Pre Loss: 0.0133447
899
+ 2024-11-13 04:35:10,043 - Epoch 85: Lr: 0.0006171 | Train Loss: 0.0369626 | Vali Loss: 0.0379119 | Rec Loss: 0.0137643 | Latent Loss: 0.0241476 | Pre Loss: 0.0133828
900
+ 2024-11-13 04:45:09,696 - Epoch 86: Lr: 0.0006095 | Train Loss: 0.0373805 | Vali Loss: 0.0375386 | Rec Loss: 0.0136933 | Latent Loss: 0.0238454 | Pre Loss: 0.0131809
901
+ 2024-11-13 04:55:13,719 - Epoch 87: Lr: 0.0006018 | Train Loss: 0.0376037 | Vali Loss: 0.0367576 | Rec Loss: 0.0134632 | Latent Loss: 0.0232945 | Pre Loss: 0.0129441
902
+ 2024-11-13 05:05:23,902 - Epoch 88: Lr: 0.0005941 | Train Loss: 0.0370181 | Vali Loss: 0.0380912 | Rec Loss: 0.0137515 | Latent Loss: 0.0243397 | Pre Loss: 0.0134377
903
+ 2024-11-13 05:15:35,320 - Epoch 89: Lr: 0.0005864 | Train Loss: 0.0366393 | Vali Loss: 0.0372555 | Rec Loss: 0.0136550 | Latent Loss: 0.0236005 | Pre Loss: 0.0131919
904
+ 2024-11-13 05:25:47,911 - Epoch 90: Lr: 0.0005786 | Train Loss: 0.0369846 | Vali Loss: 0.0362763 | Rec Loss: 0.0134288 | Latent Loss: 0.0228476 | Pre Loss: 0.0129606
905
+ 2024-11-13 05:36:07,152 - Epoch 91: Lr: 0.0005709 | Train Loss: 0.0360251 | Vali Loss: 0.0359376 | Rec Loss: 0.0131509 | Latent Loss: 0.0227867 | Pre Loss: 0.0125168
906
+ 2024-11-13 05:46:28,076 - Epoch 92: Lr: 0.0005631 | Train Loss: 0.0353120 | Vali Loss: 0.0362496 | Rec Loss: 0.0133410 | Latent Loss: 0.0229086 | Pre Loss: 0.0128468
907
+ 2024-11-13 05:56:51,841 - Epoch 93: Lr: 0.0005553 | Train Loss: 0.0360267 | Vali Loss: 0.0360484 | Rec Loss: 0.0132952 | Latent Loss: 0.0227533 | Pre Loss: 0.0127923
908
+ 2024-11-13 06:07:16,382 - Epoch 94: Lr: 0.0005475 | Train Loss: 0.0361931 | Vali Loss: 0.0367969 | Rec Loss: 0.0130779 | Latent Loss: 0.0237190 | Pre Loss: 0.0124806
909
+ 2024-11-13 06:17:47,304 - Epoch 95: Lr: 0.0005397 | Train Loss: 0.0362583 | Vali Loss: 0.0355606 | Rec Loss: 0.0130180 | Latent Loss: 0.0225426 | Pre Loss: 0.0123812
910
+ 2024-11-13 06:28:22,735 - Epoch 96: Lr: 0.0005319 | Train Loss: 0.0360632 | Vali Loss: 0.0379306 | Rec Loss: 0.0133811 | Latent Loss: 0.0245495 | Pre Loss: 0.0129437
911
+ 2024-11-13 06:38:59,763 - Epoch 97: Lr: 0.0005240 | Train Loss: 0.0366763 | Vali Loss: 0.0373419 | Rec Loss: 0.0131426 | Latent Loss: 0.0241994 | Pre Loss: 0.0127685
912
+ 2024-11-13 06:49:40,052 - Epoch 98: Lr: 0.0005162 | Train Loss: 0.0370155 | Vali Loss: 0.0373686 | Rec Loss: 0.0130701 | Latent Loss: 0.0242986 | Pre Loss: 0.0125748
913
+ 2024-11-13 07:00:24,606 - Epoch 99: Lr: 0.0005083 | Train Loss: 0.0366915 | Vali Loss: 0.0378722 | Rec Loss: 0.0132745 | Latent Loss: 0.0245977 | Pre Loss: 0.0127006
914
+ 2024-11-13 07:11:12,106 - Epoch 100: Lr: 0.0005005 | Train Loss: 0.0372017 | Vali Loss: 0.0364578 | Rec Loss: 0.0131736 | Latent Loss: 0.0232842 | Pre Loss: 0.0126272
915
+ 2024-11-13 07:22:02,866 - Epoch 101: Lr: 0.0004927 | Train Loss: 0.0368155 | Vali Loss: 0.0367904 | Rec Loss: 0.0130749 | Latent Loss: 0.0237155 | Pre Loss: 0.0124589
916
+ 2024-11-13 07:32:54,116 - Epoch 102: Lr: 0.0004848 | Train Loss: 0.0365907 | Vali Loss: 0.0384306 | Rec Loss: 0.0134194 | Latent Loss: 0.0250112 | Pre Loss: 0.0128222
917
+ 2024-11-13 07:43:56,416 - Epoch 103: Lr: 0.0004770 | Train Loss: 0.0367178 | Vali Loss: 0.0363197 | Rec Loss: 0.0128479 | Latent Loss: 0.0234719 | Pre Loss: 0.0122695
918
+ 2024-11-13 07:54:55,476 - Epoch 104: Lr: 0.0004691 | Train Loss: 0.0363133 | Vali Loss: 0.0377730 | Rec Loss: 0.0128380 | Latent Loss: 0.0249350 | Pre Loss: 0.0122910
919
+ 2024-11-13 08:05:54,321 - Epoch 105: Lr: 0.0004613 | Train Loss: 0.0369966 | Vali Loss: 0.0371554 | Rec Loss: 0.0128336 | Latent Loss: 0.0243219 | Pre Loss: 0.0122996
920
+ 2024-11-13 08:16:56,946 - Epoch 106: Lr: 0.0004535 | Train Loss: 0.0375038 | Vali Loss: 0.0374710 | Rec Loss: 0.0130063 | Latent Loss: 0.0244647 | Pre Loss: 0.0123708
921
+ 2024-11-13 08:28:03,010 - Epoch 107: Lr: 0.0004457 | Train Loss: 0.0368209 | Vali Loss: 0.0368753 | Rec Loss: 0.0127151 | Latent Loss: 0.0241603 | Pre Loss: 0.0122661
922
+ 2024-11-13 08:39:15,905 - Epoch 108: Lr: 0.0004379 | Train Loss: 0.0365304 | Vali Loss: 0.0383509 | Rec Loss: 0.0128394 | Latent Loss: 0.0255115 | Pre Loss: 0.0123024
923
+ 2024-11-13 08:50:27,431 - Epoch 109: Lr: 0.0004301 | Train Loss: 0.0375829 | Vali Loss: 0.0365726 | Rec Loss: 0.0127646 | Latent Loss: 0.0238080 | Pre Loss: 0.0121941
924
+ 2024-11-13 09:01:42,656 - Epoch 110: Lr: 0.0004224 | Train Loss: 0.0371245 | Vali Loss: 0.0374195 | Rec Loss: 0.0127459 | Latent Loss: 0.0246737 | Pre Loss: 0.0121895
925
+ 2024-11-13 09:13:03,864 - Epoch 111: Lr: 0.0004146 | Train Loss: 0.0363739 | Vali Loss: 0.0370379 | Rec Loss: 0.0127691 | Latent Loss: 0.0242689 | Pre Loss: 0.0122089
926
+ 2024-11-13 09:24:30,996 - Epoch 112: Lr: 0.0004069 | Train Loss: 0.0363683 | Vali Loss: 0.0371355 | Rec Loss: 0.0128249 | Latent Loss: 0.0243107 | Pre Loss: 0.0123073
927
+ 2024-11-13 09:35:58,870 - Epoch 113: Lr: 0.0003992 | Train Loss: 0.0368683 | Vali Loss: 0.0373291 | Rec Loss: 0.0128375 | Latent Loss: 0.0244916 | Pre Loss: 0.0122977
928
+ 2024-11-13 09:47:30,119 - Epoch 114: Lr: 0.0003915 | Train Loss: 0.0362472 | Vali Loss: 0.0365146 | Rec Loss: 0.0126342 | Latent Loss: 0.0238804 | Pre Loss: 0.0120941
929
+ 2024-11-13 09:59:06,889 - Epoch 115: Lr: 0.0003839 | Train Loss: 0.0367525 | Vali Loss: 0.0364834 | Rec Loss: 0.0127618 | Latent Loss: 0.0237215 | Pre Loss: 0.0121414
930
+ 2024-11-13 10:10:44,409 - Epoch 116: Lr: 0.0003763 | Train Loss: 0.0363697 | Vali Loss: 0.0360516 | Rec Loss: 0.0125708 | Latent Loss: 0.0234808 | Pre Loss: 0.0119722
931
+ 2024-11-13 10:22:26,416 - Epoch 117: Lr: 0.0003687 | Train Loss: 0.0355757 | Vali Loss: 0.0368120 | Rec Loss: 0.0126076 | Latent Loss: 0.0242044 | Pre Loss: 0.0119823
932
+ 2024-11-13 10:34:12,516 - Epoch 118: Lr: 0.0003611 | Train Loss: 0.0359404 | Vali Loss: 0.0368372 | Rec Loss: 0.0127527 | Latent Loss: 0.0240844 | Pre Loss: 0.0121151
933
+ 2024-11-13 10:46:02,735 - Epoch 119: Lr: 0.0003536 | Train Loss: 0.0359532 | Vali Loss: 0.0363683 | Rec Loss: 0.0125431 | Latent Loss: 0.0238252 | Pre Loss: 0.0119990
934
+ 2024-11-13 10:57:57,334 - Epoch 120: Lr: 0.0003461 | Train Loss: 0.0363805 | Vali Loss: 0.0371629 | Rec Loss: 0.0127177 | Latent Loss: 0.0244452 | Pre Loss: 0.0120852
935
+ 2024-11-13 11:09:54,432 - Epoch 121: Lr: 0.0003387 | Train Loss: 0.0364508 | Vali Loss: 0.0361884 | Rec Loss: 0.0126301 | Latent Loss: 0.0235583 | Pre Loss: 0.0121435
936
+ 2024-11-13 11:21:54,853 - Epoch 122: Lr: 0.0003313 | Train Loss: 0.0362169 | Vali Loss: 0.0362845 | Rec Loss: 0.0124173 | Latent Loss: 0.0238672 | Pre Loss: 0.0117462
937
+ 2024-11-13 11:34:00,113 - Epoch 123: Lr: 0.0003239 | Train Loss: 0.0359912 | Vali Loss: 0.0360238 | Rec Loss: 0.0125234 | Latent Loss: 0.0235004 | Pre Loss: 0.0118866
938
+ 2024-11-13 11:46:10,337 - Epoch 124: Lr: 0.0003166 | Train Loss: 0.0357540 | Vali Loss: 0.0362449 | Rec Loss: 0.0124803 | Latent Loss: 0.0237646 | Pre Loss: 0.0119524
939
+ 2024-11-13 11:58:21,811 - Epoch 125: Lr: 0.0003093 | Train Loss: 0.0355637 | Vali Loss: 0.0361819 | Rec Loss: 0.0123601 | Latent Loss: 0.0238218 | Pre Loss: 0.0117450
940
+ 2024-11-13 12:10:36,625 - Epoch 126: Lr: 0.0003021 | Train Loss: 0.0355101 | Vali Loss: 0.0359399 | Rec Loss: 0.0123531 | Latent Loss: 0.0235868 | Pre Loss: 0.0117669
941
+ 2024-11-13 12:22:56,094 - Epoch 127: Lr: 0.0002949 | Train Loss: 0.0353797 | Vali Loss: 0.0358468 | Rec Loss: 0.0124377 | Latent Loss: 0.0234091 | Pre Loss: 0.0118169
942
+ 2024-11-13 12:35:16,267 - Epoch 128: Lr: 0.0002878 | Train Loss: 0.0352728 | Vali Loss: 0.0362220 | Rec Loss: 0.0123078 | Latent Loss: 0.0239141 | Pre Loss: 0.0116543
943
+ 2024-11-13 12:47:41,111 - Epoch 129: Lr: 0.0002808 | Train Loss: 0.0355488 | Vali Loss: 0.0359658 | Rec Loss: 0.0123394 | Latent Loss: 0.0236263 | Pre Loss: 0.0117556
944
+ 2024-11-13 13:00:06,638 - Epoch 130: Lr: 0.0002737 | Train Loss: 0.0352268 | Vali Loss: 0.0355592 | Rec Loss: 0.0121590 | Latent Loss: 0.0234002 | Pre Loss: 0.0115224
945
+ 2024-11-13 13:12:41,053 - Epoch 131: Lr: 0.0002668 | Train Loss: 0.0350704 | Vali Loss: 0.0357644 | Rec Loss: 0.0124306 | Latent Loss: 0.0233338 | Pre Loss: 0.0117848
946
+ 2024-11-13 13:25:19,591 - Epoch 132: Lr: 0.0002599 | Train Loss: 0.0348435 | Vali Loss: 0.0366512 | Rec Loss: 0.0124309 | Latent Loss: 0.0242203 | Pre Loss: 0.0119191
947
+ 2024-11-13 13:37:57,115 - Epoch 133: Lr: 0.0002530 | Train Loss: 0.0351295 | Vali Loss: 0.0361797 | Rec Loss: 0.0123686 | Latent Loss: 0.0238112 | Pre Loss: 0.0117093
948
+ 2024-11-13 13:50:38,543 - Epoch 134: Lr: 0.0002462 | Train Loss: 0.0349120 | Vali Loss: 0.0356546 | Rec Loss: 0.0123070 | Latent Loss: 0.0233476 | Pre Loss: 0.0116800
949
+ 2024-11-13 14:03:23,988 - Epoch 135: Lr: 0.0002395 | Train Loss: 0.0345933 | Vali Loss: 0.0360186 | Rec Loss: 0.0122441 | Latent Loss: 0.0237745 | Pre Loss: 0.0115156
950
+ 2024-11-13 14:16:11,517 - Epoch 136: Lr: 0.0002329 | Train Loss: 0.0346003 | Vali Loss: 0.0357039 | Rec Loss: 0.0123629 | Latent Loss: 0.0233410 | Pre Loss: 0.0116873
951
+ 2024-11-13 14:29:08,269 - Epoch 137: Lr: 0.0002263 | Train Loss: 0.0345396 | Vali Loss: 0.0349320 | Rec Loss: 0.0122604 | Latent Loss: 0.0226716 | Pre Loss: 0.0115924
952
+ 2024-11-13 14:42:08,277 - Epoch 138: Lr: 0.0002197 | Train Loss: 0.0339010 | Vali Loss: 0.0350674 | Rec Loss: 0.0121405 | Latent Loss: 0.0229269 | Pre Loss: 0.0114262
953
+ 2024-11-13 14:55:14,380 - Epoch 139: Lr: 0.0002133 | Train Loss: 0.0342487 | Vali Loss: 0.0345518 | Rec Loss: 0.0122033 | Latent Loss: 0.0223485 | Pre Loss: 0.0116180
954
+ 2024-11-13 15:08:22,014 - Epoch 140: Lr: 0.0002069 | Train Loss: 0.0342416 | Vali Loss: 0.0347040 | Rec Loss: 0.0120912 | Latent Loss: 0.0226127 | Pre Loss: 0.0113986
955
+ 2024-11-13 15:21:32,365 - Epoch 141: Lr: 0.0002006 | Train Loss: 0.0337782 | Vali Loss: 0.0351397 | Rec Loss: 0.0120899 | Latent Loss: 0.0230498 | Pre Loss: 0.0114778
956
+ 2024-11-13 15:34:43,167 - Epoch 142: Lr: 0.0001944 | Train Loss: 0.0337270 | Vali Loss: 0.0343302 | Rec Loss: 0.0119587 | Latent Loss: 0.0223716 | Pre Loss: 0.0113135
957
+ 2024-11-13 15:48:02,707 - Epoch 143: Lr: 0.0001882 | Train Loss: 0.0337138 | Vali Loss: 0.0339653 | Rec Loss: 0.0119845 | Latent Loss: 0.0219808 | Pre Loss: 0.0113890
958
+ 2024-11-13 16:01:38,038 - Epoch 144: Lr: 0.0001821 | Train Loss: 0.0335713 | Vali Loss: 0.0338977 | Rec Loss: 0.0120272 | Latent Loss: 0.0218705 | Pre Loss: 0.0114010
959
+ 2024-11-13 16:15:07,879 - Epoch 145: Lr: 0.0001761 | Train Loss: 0.0334548 | Vali Loss: 0.0341943 | Rec Loss: 0.0120572 | Latent Loss: 0.0221370 | Pre Loss: 0.0114533
960
+ 2024-11-13 16:28:34,438 - Epoch 146: Lr: 0.0001702 | Train Loss: 0.0329147 | Vali Loss: 0.0338438 | Rec Loss: 0.0120235 | Latent Loss: 0.0218203 | Pre Loss: 0.0113722
961
+ 2024-11-13 16:42:08,793 - Epoch 147: Lr: 0.0001643 | Train Loss: 0.0330750 | Vali Loss: 0.0341052 | Rec Loss: 0.0119992 | Latent Loss: 0.0221059 | Pre Loss: 0.0113597
962
+ 2024-11-13 16:55:45,404 - Epoch 148: Lr: 0.0001586 | Train Loss: 0.0327575 | Vali Loss: 0.0336969 | Rec Loss: 0.0119525 | Latent Loss: 0.0217444 | Pre Loss: 0.0113182
963
+ 2024-11-13 17:10:37,209 - Epoch 149: Lr: 0.0001529 | Train Loss: 0.0329790 | Vali Loss: 0.0337609 | Rec Loss: 0.0118945 | Latent Loss: 0.0218664 | Pre Loss: 0.0112231
964
+ 2024-11-13 17:30:58,802 - Epoch 150: Lr: 0.0001473 | Train Loss: 0.0332622 | Vali Loss: 0.0334425 | Rec Loss: 0.0119639 | Latent Loss: 0.0214787 | Pre Loss: 0.0112908
965
+ 2024-11-13 17:47:36,868 - Epoch 151: Lr: 0.0001418 | Train Loss: 0.0326990 | Vali Loss: 0.0331087 | Rec Loss: 0.0119279 | Latent Loss: 0.0211808 | Pre Loss: 0.0112699
966
+ 2024-11-13 18:01:42,464 - Epoch 152: Lr: 0.0001364 | Train Loss: 0.0322676 | Vali Loss: 0.0337667 | Rec Loss: 0.0118625 | Latent Loss: 0.0219042 | Pre Loss: 0.0112244
967
+ 2024-11-13 18:15:32,336 - Epoch 153: Lr: 0.0001311 | Train Loss: 0.0322455 | Vali Loss: 0.0332881 | Rec Loss: 0.0119097 | Latent Loss: 0.0213784 | Pre Loss: 0.0112521
968
+ 2024-11-13 18:29:21,786 - Epoch 154: Lr: 0.0001258 | Train Loss: 0.0323438 | Vali Loss: 0.0329069 | Rec Loss: 0.0118985 | Latent Loss: 0.0210084 | Pre Loss: 0.0112434
969
+ 2024-11-13 18:43:21,656 - Epoch 155: Lr: 0.0001207 | Train Loss: 0.0318821 | Vali Loss: 0.0326818 | Rec Loss: 0.0117788 | Latent Loss: 0.0209030 | Pre Loss: 0.0110836
970
+ 2024-11-13 18:57:26,284 - Epoch 156: Lr: 0.0001156 | Train Loss: 0.0315599 | Vali Loss: 0.0326506 | Rec Loss: 0.0118655 | Latent Loss: 0.0207851 | Pre Loss: 0.0111793
971
+ 2024-11-13 19:11:28,568 - Epoch 157: Lr: 0.0001107 | Train Loss: 0.0316597 | Vali Loss: 0.0321176 | Rec Loss: 0.0119158 | Latent Loss: 0.0202018 | Pre Loss: 0.0112825
972
+ 2024-11-13 19:25:36,463 - Epoch 158: Lr: 0.0001058 | Train Loss: 0.0313754 | Vali Loss: 0.0323011 | Rec Loss: 0.0117968 | Latent Loss: 0.0205043 | Pre Loss: 0.0111712
973
+ 2024-11-13 19:39:48,035 - Epoch 159: Lr: 0.0001011 | Train Loss: 0.0313783 | Vali Loss: 0.0319316 | Rec Loss: 0.0117812 | Latent Loss: 0.0201504 | Pre Loss: 0.0110983
974
+ 2024-11-13 19:54:00,124 - Epoch 160: Lr: 0.0000964 | Train Loss: 0.0310056 | Vali Loss: 0.0319436 | Rec Loss: 0.0117452 | Latent Loss: 0.0201984 | Pre Loss: 0.0111113
975
+ 2024-11-13 20:08:11,104 - Epoch 161: Lr: 0.0000918 | Train Loss: 0.0310110 | Vali Loss: 0.0317556 | Rec Loss: 0.0116753 | Latent Loss: 0.0200803 | Pre Loss: 0.0110158
976
+ 2024-11-13 20:22:24,568 - Epoch 162: Lr: 0.0000874 | Train Loss: 0.0312359 | Vali Loss: 0.0319783 | Rec Loss: 0.0117965 | Latent Loss: 0.0201817 | Pre Loss: 0.0111016
977
+ 2024-11-13 20:36:40,088 - Epoch 163: Lr: 0.0000830 | Train Loss: 0.0307263 | Vali Loss: 0.0315194 | Rec Loss: 0.0117468 | Latent Loss: 0.0197727 | Pre Loss: 0.0110939
978
+ 2024-11-13 20:50:57,804 - Epoch 164: Lr: 0.0000788 | Train Loss: 0.0305238 | Vali Loss: 0.0309965 | Rec Loss: 0.0116697 | Latent Loss: 0.0193268 | Pre Loss: 0.0110214
979
+ 2024-11-13 21:05:19,724 - Epoch 165: Lr: 0.0000746 | Train Loss: 0.0304910 | Vali Loss: 0.0308138 | Rec Loss: 0.0117249 | Latent Loss: 0.0190888 | Pre Loss: 0.0110854
980
+ 2024-11-13 21:19:44,136 - Epoch 166: Lr: 0.0000706 | Train Loss: 0.0300001 | Vali Loss: 0.0308606 | Rec Loss: 0.0117004 | Latent Loss: 0.0191602 | Pre Loss: 0.0110311
981
+ 2024-11-13 21:34:12,496 - Epoch 167: Lr: 0.0000666 | Train Loss: 0.0299453 | Vali Loss: 0.0313340 | Rec Loss: 0.0117347 | Latent Loss: 0.0195993 | Pre Loss: 0.0111045
982
+ 2024-11-13 21:48:42,395 - Epoch 168: Lr: 0.0000628 | Train Loss: 0.0300625 | Vali Loss: 0.0307237 | Rec Loss: 0.0115786 | Latent Loss: 0.0191451 | Pre Loss: 0.0109635
983
+ 2024-11-13 22:03:17,637 - Epoch 169: Lr: 0.0000591 | Train Loss: 0.0301079 | Vali Loss: 0.0306925 | Rec Loss: 0.0115730 | Latent Loss: 0.0191195 | Pre Loss: 0.0109126
984
+ 2024-11-13 22:17:55,832 - Epoch 170: Lr: 0.0000554 | Train Loss: 0.0299060 | Vali Loss: 0.0307122 | Rec Loss: 0.0115437 | Latent Loss: 0.0191684 | Pre Loss: 0.0108732
985
+ 2024-11-13 22:32:38,714 - Epoch 171: Lr: 0.0000519 | Train Loss: 0.0295044 | Vali Loss: 0.0308895 | Rec Loss: 0.0116537 | Latent Loss: 0.0192358 | Pre Loss: 0.0110093
986
+ 2024-11-13 22:47:22,586 - Epoch 172: Lr: 0.0000485 | Train Loss: 0.0298790 | Vali Loss: 0.0304769 | Rec Loss: 0.0116211 | Latent Loss: 0.0188558 | Pre Loss: 0.0109739
987
+ 2024-11-13 23:02:11,496 - Epoch 173: Lr: 0.0000453 | Train Loss: 0.0294234 | Vali Loss: 0.0303300 | Rec Loss: 0.0116224 | Latent Loss: 0.0187076 | Pre Loss: 0.0109595
988
+ 2024-11-13 23:17:02,964 - Epoch 174: Lr: 0.0000421 | Train Loss: 0.0292904 | Vali Loss: 0.0303092 | Rec Loss: 0.0116127 | Latent Loss: 0.0186965 | Pre Loss: 0.0109421
989
+ 2024-11-13 23:32:04,207 - Epoch 175: Lr: 0.0000390 | Train Loss: 0.0292626 | Vali Loss: 0.0301656 | Rec Loss: 0.0116291 | Latent Loss: 0.0185365 | Pre Loss: 0.0109323
990
+ 2024-11-13 23:47:10,160 - Epoch 176: Lr: 0.0000361 | Train Loss: 0.0291600 | Vali Loss: 0.0300045 | Rec Loss: 0.0115661 | Latent Loss: 0.0184384 | Pre Loss: 0.0108645
991
+ 2024-11-14 00:02:21,368 - Epoch 177: Lr: 0.0000332 | Train Loss: 0.0289977 | Vali Loss: 0.0300591 | Rec Loss: 0.0115594 | Latent Loss: 0.0184996 | Pre Loss: 0.0109035
992
+ 2024-11-14 00:17:36,543 - Epoch 178: Lr: 0.0000305 | Train Loss: 0.0290346 | Vali Loss: 0.0300183 | Rec Loss: 0.0115460 | Latent Loss: 0.0184723 | Pre Loss: 0.0108723
993
+ 2024-11-14 00:32:54,871 - Epoch 179: Lr: 0.0000279 | Train Loss: 0.0289352 | Vali Loss: 0.0298609 | Rec Loss: 0.0115650 | Latent Loss: 0.0182959 | Pre Loss: 0.0109038
994
+ 2024-11-14 00:48:15,843 - Epoch 180: Lr: 0.0000254 | Train Loss: 0.0289109 | Vali Loss: 0.0297873 | Rec Loss: 0.0115294 | Latent Loss: 0.0182579 | Pre Loss: 0.0108640
995
+ 2024-11-14 01:03:39,682 - Epoch 181: Lr: 0.0000231 | Train Loss: 0.0287436 | Vali Loss: 0.0297885 | Rec Loss: 0.0115994 | Latent Loss: 0.0181890 | Pre Loss: 0.0109177
996
+ 2024-11-14 01:19:02,422 - Epoch 182: Lr: 0.0000208 | Train Loss: 0.0286875 | Vali Loss: 0.0295863 | Rec Loss: 0.0115673 | Latent Loss: 0.0180190 | Pre Loss: 0.0108633
997
+ 2024-11-14 01:34:36,382 - Epoch 183: Lr: 0.0000187 | Train Loss: 0.0285684 | Vali Loss: 0.0293864 | Rec Loss: 0.0115279 | Latent Loss: 0.0178585 | Pre Loss: 0.0108706
998
+ 2024-11-14 01:50:10,944 - Epoch 184: Lr: 0.0000167 | Train Loss: 0.0284263 | Vali Loss: 0.0295520 | Rec Loss: 0.0114974 | Latent Loss: 0.0180546 | Pre Loss: 0.0108481
999
+ 2024-11-14 02:05:49,208 - Epoch 185: Lr: 0.0000148 | Train Loss: 0.0285181 | Vali Loss: 0.0295676 | Rec Loss: 0.0115136 | Latent Loss: 0.0180540 | Pre Loss: 0.0108423
1000
+ 2024-11-14 02:21:26,571 - Epoch 186: Lr: 0.0000130 | Train Loss: 0.0285046 | Vali Loss: 0.0295303 | Rec Loss: 0.0115545 | Latent Loss: 0.0179758 | Pre Loss: 0.0108727
1001
+ 2024-11-14 02:37:12,396 - Epoch 187: Lr: 0.0000114 | Train Loss: 0.0285103 | Vali Loss: 0.0293962 | Rec Loss: 0.0114810 | Latent Loss: 0.0179152 | Pre Loss: 0.0108145
1002
+ 2024-11-14 02:53:02,494 - Epoch 188: Lr: 0.0000098 | Train Loss: 0.0284704 | Vali Loss: 0.0294403 | Rec Loss: 0.0115041 | Latent Loss: 0.0179362 | Pre Loss: 0.0108330
1003
+ 2024-11-14 03:08:50,235 - Epoch 189: Lr: 0.0000084 | Train Loss: 0.0284290 | Vali Loss: 0.0293318 | Rec Loss: 0.0114991 | Latent Loss: 0.0178327 | Pre Loss: 0.0108087
1004
+ 2024-11-14 03:24:42,482 - Epoch 190: Lr: 0.0000071 | Train Loss: 0.0284050 | Vali Loss: 0.0293675 | Rec Loss: 0.0115041 | Latent Loss: 0.0178634 | Pre Loss: 0.0108258
1005
+ 2024-11-14 03:40:39,414 - Epoch 191: Lr: 0.0000060 | Train Loss: 0.0283160 | Vali Loss: 0.0293251 | Rec Loss: 0.0114767 | Latent Loss: 0.0178485 | Pre Loss: 0.0108392
1006
+ 2024-11-14 03:56:40,525 - Epoch 192: Lr: 0.0000049 | Train Loss: 0.0283510 | Vali Loss: 0.0293785 | Rec Loss: 0.0114884 | Latent Loss: 0.0178901 | Pre Loss: 0.0108106
1007
+ 2024-11-14 04:12:42,720 - Epoch 193: Lr: 0.0000040 | Train Loss: 0.0283576 | Vali Loss: 0.0293288 | Rec Loss: 0.0114865 | Latent Loss: 0.0178423 | Pre Loss: 0.0108077
1008
+ 2024-11-14 04:28:46,784 - Epoch 194: Lr: 0.0000032 | Train Loss: 0.0283764 | Vali Loss: 0.0292748 | Rec Loss: 0.0114811 | Latent Loss: 0.0177937 | Pre Loss: 0.0108026
1009
+ 2024-11-14 04:44:57,674 - Epoch 195: Lr: 0.0000025 | Train Loss: 0.0284286 | Vali Loss: 0.0292821 | Rec Loss: 0.0115072 | Latent Loss: 0.0177749 | Pre Loss: 0.0108136
1010
+ 2024-11-14 05:01:10,809 - Epoch 196: Lr: 0.0000020 | Train Loss: 0.0282681 | Vali Loss: 0.0292596 | Rec Loss: 0.0114819 | Latent Loss: 0.0177776 | Pre Loss: 0.0108069
1011
+ 2024-11-14 05:17:26,613 - Epoch 197: Lr: 0.0000016 | Train Loss: 0.0281687 | Vali Loss: 0.0292532 | Rec Loss: 0.0114764 | Latent Loss: 0.0177768 | Pre Loss: 0.0108154
1012
+ 2024-11-14 05:33:47,302 - Epoch 198: Lr: 0.0000012 | Train Loss: 0.0283151 | Vali Loss: 0.0292646 | Rec Loss: 0.0114921 | Latent Loss: 0.0177724 | Pre Loss: 0.0108038
1013
+ 2024-11-14 05:50:11,307 - Epoch 199: Lr: 0.0000011 | Train Loss: 0.0282656 | Vali Loss: 0.0292677 | Rec Loss: 0.0114744 | Latent Loss: 0.0177933 | Pre Loss: 0.0108276
1014
+ 2024-11-14 05:53:06,170 - mse:132.8868865966797, mae:328.6748962402344, ssim:0.9086267643737793, psnr:19.906916804109503