diff --git "a/Analysis_code/2.make_oversample_data/gpu0.log" "b/Analysis_code/2.make_oversample_data/gpu0.log"
new file mode 100644--- /dev/null
+++ "b/Analysis_code/2.make_oversample_data/gpu0.log"
@@ -0,0 +1,9259 @@
+nohup: ignoring input
+/bin/bash: /opt/conda/lib/libtinfo.so.6: no version information available (required by /bin/bash)
+==========================================
+Starting CTGAN sample generation on GPU 0
+==========================================
+
+=== Processing 7000 samples ===
+Running ctgan_sample_7000_1.py...
+[I 2025-12-17 11:10:00,009] A new study created in memory with name: no-name-62666be6-ea93-4bce-83e6-c7505848095b
+[I 2025-12-17 11:10:21,026] Trial 0 finished with value: -16.958676822986835 and parameters: {'embedding_dim': 117, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -16.958676822986835.
+[I 2025-12-17 11:10:26,771] Trial 1 finished with value: -90.0565004361536 and parameters: {'embedding_dim': 71, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -16.958676822986835.
+[I 2025-12-17 11:10:36,893] Trial 2 finished with value: -6.8700827818163175 and parameters: {'embedding_dim': 109, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -6.8700827818163175.
+[I 2025-12-17 11:10:51,604] Trial 3 finished with value: -420.9820023585804 and parameters: {'embedding_dim': 108, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 2 with value: -6.8700827818163175.
+[I 2025-12-17 11:11:06,179] Trial 4 finished with value: -31.267797955799413 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 2 with value: -6.8700827818163175.
+[I 2025-12-17 11:11:20,807] Trial 5 finished with value: -103.23149007290866 and parameters: {'embedding_dim': 124, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 2 with value: -6.8700827818163175.
+[I 2025-12-17 11:11:30,842] Trial 6 finished with value: -40.6504305875223 and parameters: {'embedding_dim': 120, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -6.8700827818163175.
+[I 2025-12-17 11:11:53,702] Trial 7 finished with value: -5.7676045948218215 and parameters: {'embedding_dim': 99, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 7 with value: -5.7676045948218215.
+[I 2025-12-17 11:12:00,149] Trial 8 finished with value: -38.098984626540854 and parameters: {'embedding_dim': 81, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 7 with value: -5.7676045948218215.
+[I 2025-12-17 11:12:23,008] Trial 9 finished with value: -6.945142252710051 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 7 with value: -5.7676045948218215.
+[I 2025-12-17 11:12:53,992] Trial 10 finished with value: -62.35848386687617 and parameters: {'embedding_dim': 89, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 7 with value: -5.7676045948218215.
+[I 2025-12-17 11:13:03,950] Trial 11 finished with value: -34.54721217347493 and parameters: {'embedding_dim': 104, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 7 with value: -5.7676045948218215.
+[I 2025-12-17 11:13:17,259] Trial 12 finished with value: -17.523556530471474 and parameters: {'embedding_dim': 109, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 7 with value: -5.7676045948218215.
+[I 2025-12-17 11:13:27,056] Trial 13 finished with value: -13.402383326784395 and parameters: {'embedding_dim': 94, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 7 with value: -5.7676045948218215.
+[I 2025-12-17 11:13:32,752] Trial 14 finished with value: -6.621258002547933 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 7 with value: -5.7676045948218215.
+[I 2025-12-17 11:13:40,341] Trial 15 finished with value: -41.36895368900822 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 7 with value: -5.7676045948218215.
+[I 2025-12-17 11:13:46,267] Trial 16 finished with value: -65.33990291781267 and parameters: {'embedding_dim': 99, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 7 with value: -5.7676045948218215.
+[I 2025-12-17 11:13:53,813] Trial 17 finished with value: -6.851264163834833 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 7 with value: -5.7676045948218215.
+[I 2025-12-17 11:13:59,495] Trial 18 finished with value: -4.010865985778317 and parameters: {'embedding_dim': 90, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -4.010865985778317.
+[I 2025-12-17 11:14:14,075] Trial 19 finished with value: -228.7392304473735 and parameters: {'embedding_dim': 91, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 18 with value: -4.010865985778317.
+[I 2025-12-17 11:14:19,782] Trial 20 finished with value: -89.20841410338474 and parameters: {'embedding_dim': 88, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -4.010865985778317.
+[I 2025-12-17 11:14:25,486] Trial 21 finished with value: -293.66422139895565 and parameters: {'embedding_dim': 102, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -4.010865985778317.
+[I 2025-12-17 11:14:31,198] Trial 22 finished with value: -6.517192682791781 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -4.010865985778317.
+[I 2025-12-17 11:14:36,915] Trial 23 finished with value: -7.270040272889316 and parameters: {'embedding_dim': 116, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -4.010865985778317.
+[I 2025-12-17 11:14:42,592] Trial 24 finished with value: -76.1506268621222 and parameters: {'embedding_dim': 113, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -4.010865985778317.
+[I 2025-12-17 11:15:05,336] Trial 25 finished with value: -14.806594086912861 and parameters: {'embedding_dim': 75, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 18 with value: -4.010865985778317.
+[I 2025-12-17 11:15:12,872] Trial 26 finished with value: -93.28150223267565 and parameters: {'embedding_dim': 124, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 18 with value: -4.010865985778317.
+[I 2025-12-17 11:15:27,564] Trial 27 finished with value: -15.578828226170488 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 18 with value: -4.010865985778317.
+[I 2025-12-17 11:15:33,318] Trial 28 finished with value: -4.179004400208213 and parameters: {'embedding_dim': 85, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -4.010865985778317.
+[I 2025-12-17 11:15:40,879] Trial 29 finished with value: -20.154799214673982 and parameters: {'embedding_dim': 84, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 18 with value: -4.010865985778317.
+[I 2025-12-17 11:16:03,891] Trial 30 finished with value: -23.887794695781228 and parameters: {'embedding_dim': 86, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 18 with value: -4.010865985778317.
+[I 2025-12-17 11:16:09,666] Trial 31 finished with value: -31.569322179797666 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -4.010865985778317.
+[I 2025-12-17 11:16:15,371] Trial 32 finished with value: -47.226172508277266 and parameters: {'embedding_dim': 73, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -4.010865985778317.
+[I 2025-12-17 11:16:21,086] Trial 33 finished with value: -18.01478886730849 and parameters: {'embedding_dim': 96, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -4.010865985778317.
+[I 2025-12-17 11:16:26,803] Trial 34 finished with value: -86.6107742273914 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -4.010865985778317.
+[I 2025-12-17 11:16:32,534] Trial 35 finished with value: -2.5088602779451867 and parameters: {'embedding_dim': 105, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 35 with value: -2.5088602779451867.
+[I 2025-12-17 11:16:38,268] Trial 36 finished with value: -87.77126400891709 and parameters: {'embedding_dim': 105, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 35 with value: -2.5088602779451867.
+[I 2025-12-17 11:16:52,941] Trial 37 finished with value: -298.6620750248493 and parameters: {'embedding_dim': 106, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 35 with value: -2.5088602779451867.
+[I 2025-12-17 11:16:58,688] Trial 38 finished with value: -7.955402964934908 and parameters: {'embedding_dim': 110, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 35 with value: -2.5088602779451867.
+[I 2025-12-17 11:17:13,321] Trial 39 finished with value: -13.785359546136497 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 35 with value: -2.5088602779451867.
+[I 2025-12-17 11:17:19,042] Trial 40 finished with value: -32.46323891902347 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 35 with value: -2.5088602779451867.
+[I 2025-12-17 11:17:24,745] Trial 41 finished with value: -47.34600171294361 and parameters: {'embedding_dim': 66, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 35 with value: -2.5088602779451867.
+[I 2025-12-17 11:17:30,392] Trial 42 finished with value: -194.55599202353642 and parameters: {'embedding_dim': 113, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 35 with value: -2.5088602779451867.
+[I 2025-12-17 11:17:36,141] Trial 43 finished with value: -7.078757693860089 and parameters: {'embedding_dim': 120, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 35 with value: -2.5088602779451867.
+[I 2025-12-17 11:17:46,153] Trial 44 finished with value: -0.4931555014802902 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 44 with value: -0.4931555014802902.
+[I 2025-12-17 11:17:56,090] Trial 45 finished with value: -15.022363014181822 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 44 with value: -0.4931555014802902.
+[I 2025-12-17 11:18:06,069] Trial 46 finished with value: -0.6097532651653054 and parameters: {'embedding_dim': 96, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 44 with value: -0.4931555014802902.
+[I 2025-12-17 11:18:15,975] Trial 47 finished with value: -76.88686787052801 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 44 with value: -0.4931555014802902.
+[I 2025-12-17 11:18:26,026] Trial 48 finished with value: -8.096865269702544 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 44 with value: -0.4931555014802902.
+[I 2025-12-17 11:18:35,995] Trial 49 finished with value: -290.1378158500697 and parameters: {'embedding_dim': 109, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 44 with value: -0.4931555014802902.
+[I 2025-12-17 11:18:46,089] A new study created in memory with name: no-name-0d737048-221a-4f46-8114-2dd0d05116b5
+Using device: cuda
+Processing ../../data/data_for_modeling/incheon_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/incheon_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-17 11:19:25,562] Trial 0 finished with value: -821.7636827570874 and parameters: {'embedding_dim': 214, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 0 with value: -821.7636827570874.
+[I 2025-12-17 11:20:21,287] Trial 1 finished with value: -353.90190406890827 and parameters: {'embedding_dim': 485, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -353.90190406890827.
+[I 2025-12-17 11:22:13,774] Trial 2 finished with value: -516.8072146875494 and parameters: {'embedding_dim': 212, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 1 with value: -353.90190406890827.
+[I 2025-12-17 11:23:08,121] Trial 3 finished with value: -185.76319381411972 and parameters: {'embedding_dim': 166, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 3 with value: -185.76319381411972.
+[I 2025-12-17 11:24:39,411] Trial 4 finished with value: -90.77706367712344 and parameters: {'embedding_dim': 284, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 4 with value: -90.77706367712344.
+[I 2025-12-17 11:25:36,211] Trial 5 finished with value: -11.404329151744724 and parameters: {'embedding_dim': 262, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:26:21,621] Trial 6 finished with value: -977.047796667229 and parameters: {'embedding_dim': 338, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:26:44,278] Trial 7 finished with value: -2557.089761788674 and parameters: {'embedding_dim': 400, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:27:03,780] Trial 8 finished with value: -219.87761237759958 and parameters: {'embedding_dim': 272, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:27:39,860] Trial 9 finished with value: -151.99864520849408 and parameters: {'embedding_dim': 293, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:28:37,663] Trial 10 finished with value: -40.93600515316799 and parameters: {'embedding_dim': 391, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:29:33,766] Trial 11 finished with value: -620.4484958765995 and parameters: {'embedding_dim': 403, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:30:33,029] Trial 12 finished with value: -15.524038088014787 and parameters: {'embedding_dim': 377, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:31:18,254] Trial 13 finished with value: -914.1741448646801 and parameters: {'embedding_dim': 470, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:32:16,698] Trial 14 finished with value: -21.802977505524545 and parameters: {'embedding_dim': 349, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:33:32,864] Trial 15 finished with value: -85.18218563783432 and parameters: {'embedding_dim': 134, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:34:01,108] Trial 16 finished with value: -165.42000457608367 and parameters: {'embedding_dim': 229, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:35:01,023] Trial 17 finished with value: -71.37683328988341 and parameters: {'embedding_dim': 443, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:35:47,787] Trial 18 finished with value: -1254.6627428063116 and parameters: {'embedding_dim': 360, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:36:57,187] Trial 19 finished with value: -157.9032689258669 and parameters: {'embedding_dim': 255, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:37:27,650] Trial 20 finished with value: -363.56497721985187 and parameters: {'embedding_dim': 308, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:38:27,747] Trial 21 finished with value: -315.87386343722955 and parameters: {'embedding_dim': 345, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:39:23,618] Trial 22 finished with value: -120.26478125832257 and parameters: {'embedding_dim': 373, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:40:33,620] Trial 23 finished with value: -135.45361462978838 and parameters: {'embedding_dim': 442, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:41:31,893] Trial 24 finished with value: -152.53849170597059 and parameters: {'embedding_dim': 327, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:42:18,049] Trial 25 finished with value: -413.6775711236502 and parameters: {'embedding_dim': 426, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:43:06,392] Trial 26 finished with value: -102.27408315639538 and parameters: {'embedding_dim': 248, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:44:02,391] Trial 27 finished with value: -121.6800176448688 and parameters: {'embedding_dim': 506, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:44:42,778] Trial 28 finished with value: -267.4162014152729 and parameters: {'embedding_dim': 184, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:45:50,444] Trial 29 finished with value: -697.6876354027655 and parameters: {'embedding_dim': 308, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 5 with value: -11.404329151744724.
+[I 2025-12-17 11:46:50,828] A new study created in memory with name: no-name-24614dc9-5be6-4556-b053-3db3e3808855
+[I 2025-12-17 11:46:57,907] Trial 0 finished with value: -21.474104369158812 and parameters: {'embedding_dim': 119, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -21.474104369158812.
+[I 2025-12-17 11:47:04,552] Trial 1 finished with value: -14.370400071766554 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 1 with value: -14.370400071766554.
+[I 2025-12-17 11:47:07,795] Trial 2 finished with value: -97.13592887594531 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -14.370400071766554.
+[I 2025-12-17 11:47:11,157] Trial 3 finished with value: -148.1752058285005 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 1 with value: -14.370400071766554.
+[I 2025-12-17 11:47:14,507] Trial 4 finished with value: -157.31049963879144 and parameters: {'embedding_dim': 123, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 1 with value: -14.370400071766554.
+[I 2025-12-17 11:47:21,599] Trial 5 finished with value: -3.0272642202342492 and parameters: {'embedding_dim': 106, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:47:24,948] Trial 6 finished with value: -88.65377775730815 and parameters: {'embedding_dim': 85, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:47:29,717] Trial 7 finished with value: -17.58443648142061 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:47:34,483] Trial 8 finished with value: -350.8625615849437 and parameters: {'embedding_dim': 126, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:47:41,586] Trial 9 finished with value: -69.46395672862467 and parameters: {'embedding_dim': 94, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:47:48,213] Trial 10 finished with value: -32.63074832212392 and parameters: {'embedding_dim': 110, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:47:54,902] Trial 11 finished with value: -153.12020740731776 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:47:59,843] Trial 12 finished with value: -201.57855972008355 and parameters: {'embedding_dim': 96, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:48:06,490] Trial 13 finished with value: -47.97700505249961 and parameters: {'embedding_dim': 107, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:48:15,083] Trial 14 finished with value: -106.416964517987 and parameters: {'embedding_dim': 71, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:48:20,334] Trial 15 finished with value: -110.45819860724336 and parameters: {'embedding_dim': 84, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:48:26,995] Trial 16 finished with value: -18.150826564648618 and parameters: {'embedding_dim': 91, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:48:31,951] Trial 17 finished with value: -226.4978408283464 and parameters: {'embedding_dim': 116, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:48:39,092] Trial 18 finished with value: -96.11862581082674 and parameters: {'embedding_dim': 100, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:48:45,495] Trial 19 finished with value: -236.58760838335246 and parameters: {'embedding_dim': 113, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:48:50,720] Trial 20 finished with value: -7.338199798548944 and parameters: {'embedding_dim': 74, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:48:55,925] Trial 21 finished with value: -12.914154447573654 and parameters: {'embedding_dim': 71, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:49:01,121] Trial 22 finished with value: -8.7452097668574 and parameters: {'embedding_dim': 67, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:49:06,345] Trial 23 finished with value: -31.950119378377746 and parameters: {'embedding_dim': 67, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:49:11,573] Trial 24 finished with value: -67.56127844655697 and parameters: {'embedding_dim': 75, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:49:16,802] Trial 25 finished with value: -52.743505404650676 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:49:22,029] Trial 26 finished with value: -226.84752376136123 and parameters: {'embedding_dim': 89, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:49:25,412] Trial 27 finished with value: -30.56384299788826 and parameters: {'embedding_dim': 76, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:49:33,052] Trial 28 finished with value: -5.919321312857142 and parameters: {'embedding_dim': 101, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:49:38,337] Trial 29 finished with value: -32.88304621740904 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:49:41,686] Trial 30 finished with value: -88.45905149709179 and parameters: {'embedding_dim': 120, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:49:46,913] Trial 31 finished with value: -120.22872098279827 and parameters: {'embedding_dim': 98, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:49:52,252] Trial 32 finished with value: -58.48791402485922 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:49:57,616] Trial 33 finished with value: -40.61369214568828 and parameters: {'embedding_dim': 108, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:50:02,898] Trial 34 finished with value: -9.267004806000909 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:50:08,136] Trial 35 finished with value: -41.33117896385108 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:50:11,552] Trial 36 finished with value: -52.22804998282513 and parameters: {'embedding_dim': 112, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:50:16,779] Trial 37 finished with value: -31.955800154680606 and parameters: {'embedding_dim': 74, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:50:21,552] Trial 38 finished with value: -230.89383219265963 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:50:24,924] Trial 39 finished with value: -33.21455433103248 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:50:30,163] Trial 40 finished with value: -69.89601891602258 and parameters: {'embedding_dim': 104, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:50:35,393] Trial 41 finished with value: -17.60398640335753 and parameters: {'embedding_dim': 87, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:50:40,632] Trial 42 finished with value: -56.7429923643068 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:50:45,847] Trial 43 finished with value: -29.232170065531122 and parameters: {'embedding_dim': 67, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:50:51,080] Trial 44 finished with value: -6.027092770985961 and parameters: {'embedding_dim': 81, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:50:55,842] Trial 45 finished with value: -18.02179320225248 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:51:03,596] Trial 46 finished with value: -65.85809953010822 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:51:12,695] Trial 47 finished with value: -85.38843046024729 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 5 with value: -3.0272642202342492.
+[I 2025-12-17 11:51:18,851] Trial 48 finished with value: -0.25074543197165144 and parameters: {'embedding_dim': 67, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 48 with value: -0.25074543197165144.
+[I 2025-12-17 11:51:22,112] Trial 49 finished with value: -62.209136486168916 and parameters: {'embedding_dim': 84, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 48 with value: -0.25074543197165144.
+[I 2025-12-17 11:51:27,455] A new study created in memory with name: no-name-e8eb1e76-364e-4e5c-9482-03e4325320d3
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_7000_1_incheon_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_7000_1_incheon_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan7000_1_incheon.csv: Class 0=6683 | Class 1=6793
+Saved ../../data/data_oversampled/ctgan7000/ctgan7000_1_incheon.csv: Class 0=6683 | Class 1=6793 | Class 2=14554
+Processing ../../data/data_for_modeling/seoul_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/seoul_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-17 11:51:44,372] Trial 0 finished with value: -500.3546555551851 and parameters: {'embedding_dim': 507, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 0 with value: -500.3546555551851.
+[I 2025-12-17 11:52:04,856] Trial 1 finished with value: -440.4675834157054 and parameters: {'embedding_dim': 218, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 1 with value: -440.4675834157054.
+[I 2025-12-17 11:52:57,642] Trial 2 finished with value: -110.69551234225598 and parameters: {'embedding_dim': 373, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -110.69551234225598.
+[I 2025-12-17 11:54:06,334] Trial 3 finished with value: -17.816582550957435 and parameters: {'embedding_dim': 366, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 3 with value: -17.816582550957435.
+[I 2025-12-17 11:54:21,997] Trial 4 finished with value: -907.9292592526531 and parameters: {'embedding_dim': 304, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 3 with value: -17.816582550957435.
+[I 2025-12-17 11:54:59,183] Trial 5 finished with value: -1313.8477278139762 and parameters: {'embedding_dim': 436, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 3 with value: -17.816582550957435.
+[I 2025-12-17 11:55:13,240] Trial 6 finished with value: -1917.1214665606433 and parameters: {'embedding_dim': 403, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 3 with value: -17.816582550957435.
+[I 2025-12-17 11:55:30,393] Trial 7 finished with value: -740.2383232258178 and parameters: {'embedding_dim': 288, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 3 with value: -17.816582550957435.
+[I 2025-12-17 11:56:35,772] Trial 8 finished with value: -410.45351749890864 and parameters: {'embedding_dim': 411, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 3 with value: -17.816582550957435.
+[I 2025-12-17 11:56:50,439] Trial 9 finished with value: -2173.5156815186356 and parameters: {'embedding_dim': 445, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 3 with value: -17.816582550957435.
+[I 2025-12-17 11:58:12,835] Trial 10 finished with value: -502.1570020011967 and parameters: {'embedding_dim': 144, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 3 with value: -17.816582550957435.
+[I 2025-12-17 11:59:08,021] Trial 11 finished with value: -45.282943259501835 and parameters: {'embedding_dim': 349, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 3 with value: -17.816582550957435.
+[I 2025-12-17 12:00:12,916] Trial 12 finished with value: -170.16966331825353 and parameters: {'embedding_dim': 340, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 3 with value: -17.816582550957435.
+[I 2025-12-17 12:00:52,268] Trial 13 finished with value: -407.726628356143 and parameters: {'embedding_dim': 253, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 3 with value: -17.816582550957435.
+[I 2025-12-17 12:01:34,017] Trial 14 finished with value: -877.502182484384 and parameters: {'embedding_dim': 349, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 3 with value: -17.816582550957435.
+[I 2025-12-17 12:02:27,871] Trial 15 finished with value: -657.4328832758082 and parameters: {'embedding_dim': 496, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 3 with value: -17.816582550957435.
+[I 2025-12-17 12:03:33,282] Trial 16 finished with value: -101.73751693989016 and parameters: {'embedding_dim': 193, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 3 with value: -17.816582550957435.
+[I 2025-12-17 12:03:46,465] Trial 17 finished with value: -276.69042267111934 and parameters: {'embedding_dim': 279, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 3 with value: -17.816582550957435.
+[I 2025-12-17 12:05:08,832] Trial 18 finished with value: -602.9294704344486 and parameters: {'embedding_dim': 370, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 3 with value: -17.816582550957435.
+[I 2025-12-17 12:06:21,270] Trial 19 finished with value: -2.872103506204528 and parameters: {'embedding_dim': 464, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 19 with value: -2.872103506204528.
+[I 2025-12-17 12:06:38,231] Trial 20 finished with value: -1125.1289257774029 and parameters: {'embedding_dim': 475, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 19 with value: -2.872103506204528.
+[I 2025-12-17 12:07:33,267] Trial 21 finished with value: -262.62364127309195 and parameters: {'embedding_dim': 402, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 19 with value: -2.872103506204528.
+[I 2025-12-17 12:08:28,250] Trial 22 finished with value: -96.27738919979177 and parameters: {'embedding_dim': 445, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 19 with value: -2.872103506204528.
+[I 2025-12-17 12:09:33,868] Trial 23 finished with value: -627.8052501120043 and parameters: {'embedding_dim': 315, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 19 with value: -2.872103506204528.
+[I 2025-12-17 12:10:52,205] Trial 24 finished with value: -165.9886563625875 and parameters: {'embedding_dim': 373, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 19 with value: -2.872103506204528.
+[I 2025-12-17 12:11:57,445] Trial 25 finished with value: -392.1014728522503 and parameters: {'embedding_dim': 334, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 19 with value: -2.872103506204528.
+[I 2025-12-17 12:12:37,123] Trial 26 finished with value: -64.60871913316971 and parameters: {'embedding_dim': 471, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 19 with value: -2.872103506204528.
+[I 2025-12-17 12:13:29,749] Trial 27 finished with value: -76.62029876443188 and parameters: {'embedding_dim': 260, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 19 with value: -2.872103506204528.
+[I 2025-12-17 12:13:47,669] Trial 28 finished with value: -485.25627786003724 and parameters: {'embedding_dim': 416, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 19 with value: -2.872103506204528.
+[I 2025-12-17 12:15:07,023] Trial 29 finished with value: -1033.5126135494058 and parameters: {'embedding_dim': 493, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 19 with value: -2.872103506204528.
+[I 2025-12-17 12:16:13,014] A new study created in memory with name: no-name-b06e1df7-3189-43a1-a45b-5fde225f4a27
+[I 2025-12-17 12:16:20,183] Trial 0 finished with value: -7.068092012124022 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:16:23,484] Trial 1 finished with value: -55.30883986468918 and parameters: {'embedding_dim': 99, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:16:26,699] Trial 2 finished with value: -24.912861742418155 and parameters: {'embedding_dim': 65, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:16:31,743] Trial 3 finished with value: -81.6446381368078 and parameters: {'embedding_dim': 123, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:16:37,043] Trial 4 finished with value: -188.74323210478443 and parameters: {'embedding_dim': 101, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:16:40,486] Trial 5 finished with value: -24.873148916714428 and parameters: {'embedding_dim': 114, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:16:47,709] Trial 6 finished with value: -220.26249509588635 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:16:52,756] Trial 7 finished with value: -29.86270661860485 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:16:58,070] Trial 8 finished with value: -47.11404288179853 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:17:02,938] Trial 9 finished with value: -28.57858754726951 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:17:10,161] Trial 10 finished with value: -107.11767667040631 and parameters: {'embedding_dim': 75, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:17:13,633] Trial 11 finished with value: -176.7313036958787 and parameters: {'embedding_dim': 118, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:17:20,844] Trial 12 finished with value: -108.47712884047544 and parameters: {'embedding_dim': 112, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:17:24,313] Trial 13 finished with value: -74.37003568199282 and parameters: {'embedding_dim': 111, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:17:31,539] Trial 14 finished with value: -30.109235986029194 and parameters: {'embedding_dim': 83, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:17:38,096] Trial 15 finished with value: -46.1950874092243 and parameters: {'embedding_dim': 107, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:17:41,547] Trial 16 finished with value: -36.54604753877067 and parameters: {'embedding_dim': 128, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:17:46,860] Trial 17 finished with value: -10.558007771133411 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:17:51,656] Trial 18 finished with value: -128.63733893185443 and parameters: {'embedding_dim': 83, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:17:58,342] Trial 19 finished with value: -33.5126969871319 and parameters: {'embedding_dim': 72, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:18:03,685] Trial 20 finished with value: -28.17343875281651 and parameters: {'embedding_dim': 89, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:18:07,200] Trial 21 finished with value: -14.226506229868763 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:18:12,519] Trial 22 finished with value: -39.03556111340286 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:18:19,721] Trial 23 finished with value: -14.49510680965039 and parameters: {'embedding_dim': 79, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -7.068092012124022.
+[I 2025-12-17 12:18:23,161] Trial 24 finished with value: -5.290729858986952 and parameters: {'embedding_dim': 68, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 24 with value: -5.290729858986952.
+[I 2025-12-17 12:18:28,477] Trial 25 finished with value: -17.63557168400608 and parameters: {'embedding_dim': 65, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -5.290729858986952.
+[I 2025-12-17 12:18:33,807] Trial 26 finished with value: -70.48475638922022 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -5.290729858986952.
+[I 2025-12-17 12:18:37,256] Trial 27 finished with value: -48.041580018487615 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 24 with value: -5.290729858986952.
+[I 2025-12-17 12:18:43,981] Trial 28 finished with value: -59.92624316930932 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 24 with value: -5.290729858986952.
+[I 2025-12-17 12:18:47,182] Trial 29 finished with value: -17.521573390184333 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 24 with value: -5.290729858986952.
+[I 2025-12-17 12:18:52,213] Trial 30 finished with value: -55.6684046926566 and parameters: {'embedding_dim': 70, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -5.290729858986952.
+[I 2025-12-17 12:18:55,755] Trial 31 finished with value: -50.76326887683744 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 24 with value: -5.290729858986952.
+[I 2025-12-17 12:18:59,398] Trial 32 finished with value: -29.96157857846569 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 24 with value: -5.290729858986952.
+[I 2025-12-17 12:19:03,074] Trial 33 finished with value: -150.10043050154758 and parameters: {'embedding_dim': 81, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 24 with value: -5.290729858986952.
+[I 2025-12-17 12:19:06,639] Trial 34 finished with value: -22.073218426037492 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 24 with value: -5.290729858986952.
+[I 2025-12-17 12:19:10,100] Trial 35 finished with value: -190.73186943067154 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 24 with value: -5.290729858986952.
+[I 2025-12-17 12:19:13,697] Trial 36 finished with value: -220.39944825639546 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 24 with value: -5.290729858986952.
+[I 2025-12-17 12:19:16,912] Trial 37 finished with value: -162.48880623020796 and parameters: {'embedding_dim': 68, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 24 with value: -5.290729858986952.
+[I 2025-12-17 12:19:21,916] Trial 38 finished with value: -103.61007649543944 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -5.290729858986952.
+[I 2025-12-17 12:19:27,236] Trial 39 finished with value: -84.31767359703673 and parameters: {'embedding_dim': 88, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -5.290729858986952.
+[I 2025-12-17 12:19:32,560] Trial 40 finished with value: -12.050287161860904 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -5.290729858986952.
+[I 2025-12-17 12:19:37,903] Trial 41 finished with value: -17.419179799521952 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -5.290729858986952.
+[I 2025-12-17 12:19:43,226] Trial 42 finished with value: -313.3855646888912 and parameters: {'embedding_dim': 98, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -5.290729858986952.
+[I 2025-12-17 12:19:48,556] Trial 43 finished with value: -100.6491325234961 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -5.290729858986952.
+[I 2025-12-17 12:19:53,870] Trial 44 finished with value: -98.72446933353392 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -5.290729858986952.
+[I 2025-12-17 12:20:01,062] Trial 45 finished with value: -22.09569777555626 and parameters: {'embedding_dim': 86, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 24 with value: -5.290729858986952.
+[I 2025-12-17 12:20:04,499] Trial 46 finished with value: -21.391309121211616 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 24 with value: -5.290729858986952.
+[I 2025-12-17 12:20:11,761] Trial 47 finished with value: -4.2269040440736445 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 47 with value: -4.2269040440736445.
+[I 2025-12-17 12:20:18,549] Trial 48 finished with value: -75.38029318083343 and parameters: {'embedding_dim': 74, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 47 with value: -4.2269040440736445.
+[I 2025-12-17 12:20:25,934] Trial 49 finished with value: -41.458329508086806 and parameters: {'embedding_dim': 86, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 47 with value: -4.2269040440736445.
+[I 2025-12-17 12:20:33,231] A new study created in memory with name: no-name-02d401cd-805e-48a0-96bc-ec3080a20011
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_7000_1_seoul_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_7000_1_seoul_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan7000_1_seoul.csv: Class 0=6418 | Class 1=6915
+Saved ../../data/data_oversampled/ctgan7000/ctgan7000_1_seoul.csv: Class 0=6418 | Class 1=6915 | Class 2=15676
+Processing ../../data/data_for_modeling/busan_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/busan_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-17 12:20:46,142] Trial 0 finished with value: -1012.7169904076343 and parameters: {'embedding_dim': 145, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 0 with value: -1012.7169904076343.
+[I 2025-12-17 12:20:56,539] Trial 1 finished with value: -279.5043840375275 and parameters: {'embedding_dim': 159, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 1 with value: -279.5043840375275.
+[I 2025-12-17 12:21:07,691] Trial 2 finished with value: -215.82077575110344 and parameters: {'embedding_dim': 207, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 2 with value: -215.82077575110344.
+[I 2025-12-17 12:21:22,283] Trial 3 finished with value: -642.6821769666765 and parameters: {'embedding_dim': 276, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 2 with value: -215.82077575110344.
+[I 2025-12-17 12:21:30,479] Trial 4 finished with value: -381.0449595225708 and parameters: {'embedding_dim': 458, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 2 with value: -215.82077575110344.
+[I 2025-12-17 12:21:40,370] Trial 5 finished with value: -1709.103057015991 and parameters: {'embedding_dim': 347, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 2 with value: -215.82077575110344.
+[I 2025-12-17 12:21:51,088] Trial 6 finished with value: -257.9742369794771 and parameters: {'embedding_dim': 323, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 2 with value: -215.82077575110344.
+[I 2025-12-17 12:22:07,026] Trial 7 finished with value: -304.6378831492277 and parameters: {'embedding_dim': 388, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 2 with value: -215.82077575110344.
+[I 2025-12-17 12:22:36,158] Trial 8 finished with value: -355.1397983605338 and parameters: {'embedding_dim': 233, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 2 with value: -215.82077575110344.
+[I 2025-12-17 12:23:10,834] Trial 9 finished with value: -381.9970684990176 and parameters: {'embedding_dim': 442, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 2 with value: -215.82077575110344.
+[I 2025-12-17 12:23:18,495] Trial 10 finished with value: -2984.2575475016083 and parameters: {'embedding_dim': 216, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 2 with value: -215.82077575110344.
+[I 2025-12-17 12:23:32,306] Trial 11 finished with value: -302.2727124981888 and parameters: {'embedding_dim': 319, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 2 with value: -215.82077575110344.
+[I 2025-12-17 12:23:39,224] Trial 12 finished with value: -27.84143038249798 and parameters: {'embedding_dim': 269, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 12 with value: -27.84143038249798.
+[I 2025-12-17 12:23:46,865] Trial 13 finished with value: -866.0349909665015 and parameters: {'embedding_dim': 210, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 12 with value: -27.84143038249798.
+[I 2025-12-17 12:23:55,192] Trial 14 finished with value: -2755.7732965768946 and parameters: {'embedding_dim': 266, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 12 with value: -27.84143038249798.
+[I 2025-12-17 12:24:05,599] Trial 15 finished with value: -463.96903022766605 and parameters: {'embedding_dim': 185, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 12 with value: -27.84143038249798.
+[I 2025-12-17 12:24:18,083] Trial 16 finished with value: -12684.309692326658 and parameters: {'embedding_dim': 265, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 12 with value: -27.84143038249798.
+[I 2025-12-17 12:24:27,690] Trial 17 finished with value: -1769.4404240176987 and parameters: {'embedding_dim': 502, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 12 with value: -27.84143038249798.
+[I 2025-12-17 12:24:35,331] Trial 18 finished with value: -2104.22791499199 and parameters: {'embedding_dim': 371, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 12 with value: -27.84143038249798.
+[I 2025-12-17 12:24:49,458] Trial 19 finished with value: -883.3275393919077 and parameters: {'embedding_dim': 287, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 12 with value: -27.84143038249798.
+[I 2025-12-17 12:25:18,891] Trial 20 finished with value: -1309.3679538275317 and parameters: {'embedding_dim': 130, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 12 with value: -27.84143038249798.
+[I 2025-12-17 12:25:32,462] Trial 21 finished with value: -514.5134111875473 and parameters: {'embedding_dim': 334, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 12 with value: -27.84143038249798.
+[I 2025-12-17 12:25:40,947] Trial 22 finished with value: -623.1278172699942 and parameters: {'embedding_dim': 299, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 12 with value: -27.84143038249798.
+[I 2025-12-17 12:25:51,640] Trial 23 finished with value: -356.80583111724764 and parameters: {'embedding_dim': 242, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 12 with value: -27.84143038249798.
+[I 2025-12-17 12:26:01,968] Trial 24 finished with value: -1145.2189580130453 and parameters: {'embedding_dim': 180, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 12 with value: -27.84143038249798.
+[I 2025-12-17 12:26:08,207] Trial 25 finished with value: -342.38661081586974 and parameters: {'embedding_dim': 376, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 12 with value: -27.84143038249798.
+[I 2025-12-17 12:26:20,908] Trial 26 finished with value: -444.92139513482334 and parameters: {'embedding_dim': 310, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 12 with value: -27.84143038249798.
+[I 2025-12-17 12:26:36,241] Trial 27 finished with value: -724.2627549738556 and parameters: {'embedding_dim': 403, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 12 with value: -27.84143038249798.
+[I 2025-12-17 12:26:54,399] Trial 28 finished with value: -3089.190312389719 and parameters: {'embedding_dim': 253, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 12 with value: -27.84143038249798.
+[I 2025-12-17 12:27:05,385] Trial 29 finished with value: -501.1343045639209 and parameters: {'embedding_dim': 189, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 12 with value: -27.84143038249798.
+[I 2025-12-17 12:27:14,465] A new study created in memory with name: no-name-05ee563b-8b0f-4360-8faa-156a7a97510b
+[I 2025-12-17 12:27:19,311] Trial 0 finished with value: -5.454173489908031 and parameters: {'embedding_dim': 121, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:27:25,840] Trial 1 finished with value: -90.54899549272709 and parameters: {'embedding_dim': 87, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:27:32,370] Trial 2 finished with value: -59.52080130178628 and parameters: {'embedding_dim': 91, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:27:35,627] Trial 3 finished with value: -81.1445060035648 and parameters: {'embedding_dim': 94, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:27:42,366] Trial 4 finished with value: -78.9915418007211 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:27:45,481] Trial 5 finished with value: -424.729826414981 and parameters: {'embedding_dim': 124, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:27:52,131] Trial 6 finished with value: -59.52763769435807 and parameters: {'embedding_dim': 96, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:27:57,110] Trial 7 finished with value: -49.24834874981865 and parameters: {'embedding_dim': 110, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:28:03,577] Trial 8 finished with value: -11.054062911661026 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:28:10,237] Trial 9 finished with value: -80.46755638705167 and parameters: {'embedding_dim': 118, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:28:15,448] Trial 10 finished with value: -65.40685257588372 and parameters: {'embedding_dim': 110, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:28:20,211] Trial 11 finished with value: -161.99393913084873 and parameters: {'embedding_dim': 68, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:28:24,952] Trial 12 finished with value: -51.663312144611695 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:28:28,076] Trial 13 finished with value: -244.16063091943715 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:28:32,832] Trial 14 finished with value: -88.5462076427367 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:28:38,041] Trial 15 finished with value: -27.868932109774804 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:28:44,359] Trial 16 finished with value: -84.1229455547961 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:28:47,442] Trial 17 finished with value: -189.4194284980554 and parameters: {'embedding_dim': 103, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:28:52,125] Trial 18 finished with value: -171.75494172860454 and parameters: {'embedding_dim': 124, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:28:57,367] Trial 19 finished with value: -184.980296129688 and parameters: {'embedding_dim': 83, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:29:03,771] Trial 20 finished with value: -115.7264208354288 and parameters: {'embedding_dim': 116, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:29:08,978] Trial 21 finished with value: -53.102856538027936 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:29:14,199] Trial 22 finished with value: -12.32936418907997 and parameters: {'embedding_dim': 128, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:29:19,405] Trial 23 finished with value: -129.00597187686174 and parameters: {'embedding_dim': 128, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:29:24,616] Trial 24 finished with value: -52.92696218846211 and parameters: {'embedding_dim': 117, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:29:27,734] Trial 25 finished with value: -326.1735733684283 and parameters: {'embedding_dim': 122, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:29:32,953] Trial 26 finished with value: -141.466535019952 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:29:39,331] Trial 27 finished with value: -194.40110500550185 and parameters: {'embedding_dim': 112, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:29:44,568] Trial 28 finished with value: -61.350463808120544 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:29:50,958] Trial 29 finished with value: -270.9872597996821 and parameters: {'embedding_dim': 87, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:29:58,083] Trial 30 finished with value: -112.38068434957165 and parameters: {'embedding_dim': 122, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:30:03,292] Trial 31 finished with value: -59.36508214612204 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:30:08,515] Trial 32 finished with value: -71.95721759613235 and parameters: {'embedding_dim': 100, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:30:13,745] Trial 33 finished with value: -46.4410821935723 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:30:18,953] Trial 34 finished with value: -219.32534308046516 and parameters: {'embedding_dim': 113, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:30:22,049] Trial 35 finished with value: -432.6186440644882 and parameters: {'embedding_dim': 107, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:30:26,985] Trial 36 finished with value: -342.8721554992195 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:30:34,059] Trial 37 finished with value: -256.765291056285 and parameters: {'embedding_dim': 97, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:30:37,271] Trial 38 finished with value: -129.19583181112864 and parameters: {'embedding_dim': 126, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:30:43,616] Trial 39 finished with value: -77.82764154281158 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:30:48,824] Trial 40 finished with value: -72.71948784410324 and parameters: {'embedding_dim': 121, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:30:54,020] Trial 41 finished with value: -204.14240411811056 and parameters: {'embedding_dim': 89, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:30:59,346] Trial 42 finished with value: -165.27686750634575 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:31:04,552] Trial 43 finished with value: -38.42296313202119 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:31:09,450] Trial 44 finished with value: -95.4557930892131 and parameters: {'embedding_dim': 114, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:31:14,645] Trial 45 finished with value: -275.8981187004693 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:31:19,362] Trial 46 finished with value: -124.16217616091166 and parameters: {'embedding_dim': 94, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:31:24,571] Trial 47 finished with value: -193.4429254917798 and parameters: {'embedding_dim': 107, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:31:29,311] Trial 48 finished with value: -166.5750204485426 and parameters: {'embedding_dim': 99, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:31:35,966] Trial 49 finished with value: -54.6645965064598 and parameters: {'embedding_dim': 110, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -5.454173489908031.
+[I 2025-12-17 12:31:40,910] A new study created in memory with name: no-name-97f854d7-de7c-4ba3-97f4-d1fcfe0cb60f
+[I 2025-12-17 12:32:02,716] Trial 0 finished with value: -736.9576210790337 and parameters: {'embedding_dim': 146, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -736.9576210790337.
+[I 2025-12-17 12:32:20,723] Trial 1 finished with value: -2666.453309560677 and parameters: {'embedding_dim': 395, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -736.9576210790337.
+[I 2025-12-17 12:32:30,768] Trial 2 finished with value: -722.7918892022223 and parameters: {'embedding_dim': 367, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 2 with value: -722.7918892022223.
+[I 2025-12-17 12:32:44,931] Trial 3 finished with value: -424.234159638869 and parameters: {'embedding_dim': 318, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 3 with value: -424.234159638869.
+[I 2025-12-17 12:33:03,689] Trial 4 finished with value: -800.0498798012828 and parameters: {'embedding_dim': 397, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 3 with value: -424.234159638869.
+[I 2025-12-17 12:33:14,663] Trial 5 finished with value: -4907.967696095072 and parameters: {'embedding_dim': 482, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 3 with value: -424.234159638869.
+[I 2025-12-17 12:33:25,149] Trial 6 finished with value: -220.2746844084473 and parameters: {'embedding_dim': 132, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 6 with value: -220.2746844084473.
+[I 2025-12-17 12:33:35,941] Trial 7 finished with value: -3450.116906184774 and parameters: {'embedding_dim': 184, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 6 with value: -220.2746844084473.
+[I 2025-12-17 12:33:52,011] Trial 8 finished with value: -196.87904603731315 and parameters: {'embedding_dim': 251, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 8 with value: -196.87904603731315.
+[I 2025-12-17 12:34:02,445] Trial 9 finished with value: -660.2401365645137 and parameters: {'embedding_dim': 385, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 8 with value: -196.87904603731315.
+[I 2025-12-17 12:34:18,398] Trial 10 finished with value: -464.09290776110225 and parameters: {'embedding_dim': 245, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 8 with value: -196.87904603731315.
+[I 2025-12-17 12:34:36,540] Trial 11 finished with value: -1436.0244829085357 and parameters: {'embedding_dim': 239, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 8 with value: -196.87904603731315.
+[I 2025-12-17 12:34:52,592] Trial 12 finished with value: -388.4858904853203 and parameters: {'embedding_dim': 133, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 8 with value: -196.87904603731315.
+[I 2025-12-17 12:35:08,614] Trial 13 finished with value: -230.4758387745408 and parameters: {'embedding_dim': 236, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 8 with value: -196.87904603731315.
+[I 2025-12-17 12:35:13,930] Trial 14 finished with value: -221.85609309152693 and parameters: {'embedding_dim': 312, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 8 with value: -196.87904603731315.
+[I 2025-12-17 12:35:22,518] Trial 15 finished with value: -837.4616486671334 and parameters: {'embedding_dim': 191, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 8 with value: -196.87904603731315.
+[I 2025-12-17 12:35:46,109] Trial 16 finished with value: -780.5984737994794 and parameters: {'embedding_dim': 279, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 8 with value: -196.87904603731315.
+[I 2025-12-17 12:36:16,422] Trial 17 finished with value: -95.40098787540165 and parameters: {'embedding_dim': 187, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 17 with value: -95.40098787540165.
+[I 2025-12-17 12:36:31,861] Trial 18 finished with value: -626.8607801192956 and parameters: {'embedding_dim': 196, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 17 with value: -95.40098787540165.
+[I 2025-12-17 12:36:43,662] Trial 19 finished with value: -499.17373662036533 and parameters: {'embedding_dim': 268, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 17 with value: -95.40098787540165.
+[I 2025-12-17 12:37:05,654] Trial 20 finished with value: -758.0215963156809 and parameters: {'embedding_dim': 462, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 17 with value: -95.40098787540165.
+[I 2025-12-17 12:37:32,994] Trial 21 finished with value: -1399.702062902588 and parameters: {'embedding_dim': 162, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 17 with value: -95.40098787540165.
+[I 2025-12-17 12:37:43,821] Trial 22 finished with value: -3091.3184905720746 and parameters: {'embedding_dim': 194, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 17 with value: -95.40098787540165.
+[I 2025-12-17 12:38:02,234] Trial 23 finished with value: -364.2868334387317 and parameters: {'embedding_dim': 219, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 17 with value: -95.40098787540165.
+[I 2025-12-17 12:38:35,268] Trial 24 finished with value: -167.60192858898301 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 17 with value: -95.40098787540165.
+[I 2025-12-17 12:39:11,014] Trial 25 finished with value: -115.15781059742393 and parameters: {'embedding_dim': 166, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 17 with value: -95.40098787540165.
+[I 2025-12-17 12:39:46,471] Trial 26 finished with value: -1425.6616650753128 and parameters: {'embedding_dim': 163, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 17 with value: -95.40098787540165.
+[I 2025-12-17 12:40:21,030] Trial 27 finished with value: -87.48401890458666 and parameters: {'embedding_dim': 217, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 27 with value: -87.48401890458666.
+[I 2025-12-17 12:40:35,366] Trial 28 finished with value: -426.3701332707577 and parameters: {'embedding_dim': 282, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 27 with value: -87.48401890458666.
+[I 2025-12-17 12:40:51,682] Trial 29 finished with value: -508.07512004171184 and parameters: {'embedding_dim': 167, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 27 with value: -87.48401890458666.
+[I 2025-12-17 12:41:27,252] A new study created in memory with name: no-name-eb54a9fc-7704-4ae2-8b1a-0ca130177acb
+[I 2025-12-17 12:41:30,845] Trial 0 finished with value: -366.1541665581818 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 0 with value: -366.1541665581818.
+[I 2025-12-17 12:41:40,544] Trial 1 finished with value: -65.09559480202361 and parameters: {'embedding_dim': 125, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 1 with value: -65.09559480202361.
+[I 2025-12-17 12:41:53,277] Trial 2 finished with value: -10.421075769716 and parameters: {'embedding_dim': 98, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:41:58,786] Trial 3 finished with value: -322.4000507209691 and parameters: {'embedding_dim': 90, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:42:08,169] Trial 4 finished with value: -37.43134885374281 and parameters: {'embedding_dim': 79, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:42:11,587] Trial 5 finished with value: -552.8942139340413 and parameters: {'embedding_dim': 88, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:42:16,324] Trial 6 finished with value: -152.0494601368586 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:42:22,481] Trial 7 finished with value: -23.37462181858609 and parameters: {'embedding_dim': 81, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:42:26,069] Trial 8 finished with value: -25.36438269322395 and parameters: {'embedding_dim': 70, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:42:31,544] Trial 9 finished with value: -84.15778729969254 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:42:45,635] Trial 10 finished with value: -20.439612809793942 and parameters: {'embedding_dim': 105, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:42:58,939] Trial 11 finished with value: -41.67185540790695 and parameters: {'embedding_dim': 106, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:43:11,529] Trial 12 finished with value: -17.36271229277249 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:43:26,252] Trial 13 finished with value: -24.540343919751884 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:43:38,890] Trial 14 finished with value: -54.57818478168671 and parameters: {'embedding_dim': 118, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:43:51,504] Trial 15 finished with value: -61.049845323583824 and parameters: {'embedding_dim': 98, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:44:06,068] Trial 16 finished with value: -361.77321287843245 and parameters: {'embedding_dim': 98, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:44:15,432] Trial 17 finished with value: -83.63327793087495 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:44:29,574] Trial 18 finished with value: -128.73298665895862 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:44:43,302] Trial 19 finished with value: -24.18455544476223 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:44:50,839] Trial 20 finished with value: -27.720329409426498 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:45:05,317] Trial 21 finished with value: -86.95969140185005 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:45:18,324] Trial 22 finished with value: -65.26889223649432 and parameters: {'embedding_dim': 96, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:45:31,852] Trial 23 finished with value: -187.11212307080413 and parameters: {'embedding_dim': 108, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:45:46,014] Trial 24 finished with value: -182.96111252990164 and parameters: {'embedding_dim': 120, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:45:55,727] Trial 25 finished with value: -96.67674110361457 and parameters: {'embedding_dim': 99, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:46:10,328] Trial 26 finished with value: -25.26330885115499 and parameters: {'embedding_dim': 102, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:46:22,724] Trial 27 finished with value: -151.87325019676925 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:46:28,337] Trial 28 finished with value: -46.097026039861014 and parameters: {'embedding_dim': 110, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:46:41,438] Trial 29 finished with value: -77.93569551782244 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:46:50,552] Trial 30 finished with value: -223.38160204793755 and parameters: {'embedding_dim': 85, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:46:55,730] Trial 31 finished with value: -183.39711040755842 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:47:00,902] Trial 32 finished with value: -236.9586228572768 and parameters: {'embedding_dim': 75, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:47:06,060] Trial 33 finished with value: -195.3262885337371 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:47:12,051] Trial 34 finished with value: -24.1314464385227 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -10.421075769716.
+[I 2025-12-17 12:47:18,075] Trial 35 finished with value: -9.422069837231707 and parameters: {'embedding_dim': 101, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 35 with value: -9.422069837231707.
+[I 2025-12-17 12:47:21,526] Trial 36 finished with value: -29.526676799295945 and parameters: {'embedding_dim': 101, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 35 with value: -9.422069837231707.
+[I 2025-12-17 12:47:34,134] Trial 37 finished with value: -111.5238228101669 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 35 with value: -9.422069837231707.
+[I 2025-12-17 12:47:39,269] Trial 38 finished with value: -257.0822208793668 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 35 with value: -9.422069837231707.
+[I 2025-12-17 12:47:42,901] Trial 39 finished with value: -55.304645722257625 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 35 with value: -9.422069837231707.
+[I 2025-12-17 12:47:48,085] Trial 40 finished with value: -112.92781235853379 and parameters: {'embedding_dim': 118, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 35 with value: -9.422069837231707.
+[I 2025-12-17 12:47:53,919] Trial 41 finished with value: -192.84125930971635 and parameters: {'embedding_dim': 90, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 35 with value: -9.422069837231707.
+[I 2025-12-17 12:48:01,116] Trial 42 finished with value: -12.327808506450946 and parameters: {'embedding_dim': 101, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 35 with value: -9.422069837231707.
+[I 2025-12-17 12:48:06,201] Trial 43 finished with value: -355.3591973041408 and parameters: {'embedding_dim': 101, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 35 with value: -9.422069837231707.
+[I 2025-12-17 12:48:11,384] Trial 44 finished with value: -172.70312276977774 and parameters: {'embedding_dim': 109, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 35 with value: -9.422069837231707.
+[I 2025-12-17 12:48:24,070] Trial 45 finished with value: -39.314658866011385 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 35 with value: -9.422069837231707.
+[I 2025-12-17 12:48:29,237] Trial 46 finished with value: -49.520322355932244 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 35 with value: -9.422069837231707.
+[I 2025-12-17 12:48:36,574] Trial 47 finished with value: -192.10540880027668 and parameters: {'embedding_dim': 98, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 35 with value: -9.422069837231707.
+[I 2025-12-17 12:48:49,215] Trial 48 finished with value: -78.12404884354544 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 35 with value: -9.422069837231707.
+[I 2025-12-17 12:48:57,057] Trial 49 finished with value: -21.215393034988768 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 35 with value: -9.422069837231707.
+[I 2025-12-17 12:49:02,489] A new study created in memory with name: no-name-571c726d-80ea-456a-8cbf-f787d91ba14b
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_7000_1_busan_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_7000_1_busan_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan7000_1_busan.csv: Class 0=5499 | Class 1=6204
+Saved ../../data/data_oversampled/ctgan7000/ctgan7000_1_busan.csv: Class 0=5499 | Class 1=6204 | Class 2=16492
+Processing ../../data/data_for_modeling/daegu_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/daegu_train.csv: Optimizing CTGAN for class 1...
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_7000_1_daegu_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_7000_1_daegu_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan7000_1_daegu.csv: Class 0=6375 | Class 1=6626
+Saved ../../data/data_oversampled/ctgan7000/ctgan7000_1_daegu.csv: Class 0=6375 | Class 1=6626 | Class 2=16582
+Processing ../../data/data_for_modeling/daejeon_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/daejeon_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-17 12:50:01,536] Trial 0 finished with value: -169.24730726379008 and parameters: {'embedding_dim': 455, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -169.24730726379008.
+[I 2025-12-17 12:50:24,977] Trial 1 finished with value: -394.71071542666243 and parameters: {'embedding_dim': 400, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 0 with value: -169.24730726379008.
+[I 2025-12-17 12:50:53,957] Trial 2 finished with value: -514.6040901204162 and parameters: {'embedding_dim': 482, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 0 with value: -169.24730726379008.
+[I 2025-12-17 12:51:09,012] Trial 3 finished with value: -784.002911986915 and parameters: {'embedding_dim': 213, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 0 with value: -169.24730726379008.
+[I 2025-12-17 12:51:44,398] Trial 4 finished with value: -178.9417463639661 and parameters: {'embedding_dim': 369, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 0 with value: -169.24730726379008.
+[I 2025-12-17 12:53:04,757] Trial 5 finished with value: -673.4729252789606 and parameters: {'embedding_dim': 156, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 0 with value: -169.24730726379008.
+[I 2025-12-17 12:53:58,444] Trial 6 finished with value: -350.82503206519584 and parameters: {'embedding_dim': 138, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -169.24730726379008.
+[I 2025-12-17 12:54:54,471] Trial 7 finished with value: -290.2817254744043 and parameters: {'embedding_dim': 325, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -169.24730726379008.
+[I 2025-12-17 12:55:15,639] Trial 8 finished with value: -349.837926671086 and parameters: {'embedding_dim': 290, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 0 with value: -169.24730726379008.
+[I 2025-12-17 12:55:31,530] Trial 9 finished with value: -269.75147578908275 and parameters: {'embedding_dim': 371, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 0 with value: -169.24730726379008.
+[I 2025-12-17 12:55:59,349] Trial 10 finished with value: -17.33229140176314 and parameters: {'embedding_dim': 497, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 10 with value: -17.33229140176314.
+[I 2025-12-17 12:56:27,778] Trial 11 finished with value: -294.07291367942656 and parameters: {'embedding_dim': 512, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 10 with value: -17.33229140176314.
+[I 2025-12-17 12:57:09,223] Trial 12 finished with value: -300.2909532247963 and parameters: {'embedding_dim': 448, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -17.33229140176314.
+[I 2025-12-17 12:57:49,525] Trial 13 finished with value: -443.330454203609 and parameters: {'embedding_dim': 446, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -17.33229140176314.
+[I 2025-12-17 12:58:30,200] Trial 14 finished with value: -67.15556525447316 and parameters: {'embedding_dim': 436, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -17.33229140176314.
+[I 2025-12-17 12:59:11,271] Trial 15 finished with value: -232.09973293430275 and parameters: {'embedding_dim': 512, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -17.33229140176314.
+[I 2025-12-17 12:59:38,662] Trial 16 finished with value: -990.8252289191684 and parameters: {'embedding_dim': 403, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 10 with value: -17.33229140176314.
+[I 2025-12-17 13:00:18,478] Trial 17 finished with value: -575.713743293899 and parameters: {'embedding_dim': 291, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -17.33229140176314.
+[I 2025-12-17 13:00:27,136] Trial 18 finished with value: -801.5941136619956 and parameters: {'embedding_dim': 418, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 10 with value: -17.33229140176314.
+[I 2025-12-17 13:00:48,531] Trial 19 finished with value: -896.3611895956426 and parameters: {'embedding_dim': 343, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 10 with value: -17.33229140176314.
+[I 2025-12-17 13:01:55,347] Trial 20 finished with value: -255.0193439206809 and parameters: {'embedding_dim': 479, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 10 with value: -17.33229140176314.
+[I 2025-12-17 13:03:04,530] Trial 21 finished with value: -54.158592739314116 and parameters: {'embedding_dim': 452, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 10 with value: -17.33229140176314.
+[I 2025-12-17 13:04:15,836] Trial 22 finished with value: -58.556918417257464 and parameters: {'embedding_dim': 426, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 10 with value: -17.33229140176314.
+[I 2025-12-17 13:05:29,492] Trial 23 finished with value: -693.9097667652926 and parameters: {'embedding_dim': 474, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 10 with value: -17.33229140176314.
+[I 2025-12-17 13:06:44,147] Trial 24 finished with value: -107.31658734666027 and parameters: {'embedding_dim': 382, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 10 with value: -17.33229140176314.
+[I 2025-12-17 13:07:58,171] Trial 25 finished with value: -678.2888718238218 and parameters: {'embedding_dim': 481, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 10 with value: -17.33229140176314.
+[I 2025-12-17 13:09:11,767] Trial 26 finished with value: -69.29112657317782 and parameters: {'embedding_dim': 427, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 10 with value: -17.33229140176314.
+[I 2025-12-17 13:10:36,421] Trial 27 finished with value: -296.25141267450186 and parameters: {'embedding_dim': 266, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 10 with value: -17.33229140176314.
+[I 2025-12-17 13:11:11,852] Trial 28 finished with value: -69.42281927758532 and parameters: {'embedding_dim': 510, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 10 with value: -17.33229140176314.
+[I 2025-12-17 13:11:32,451] Trial 29 finished with value: -367.319254351256 and parameters: {'embedding_dim': 459, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 10 with value: -17.33229140176314.
+[I 2025-12-17 13:11:59,185] A new study created in memory with name: no-name-96c0f44a-dc3a-4410-b1b3-b85f04dd8032
+[I 2025-12-17 13:12:02,678] Trial 0 finished with value: -35.9324435462535 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -35.9324435462535.
+[I 2025-12-17 13:12:07,566] Trial 1 finished with value: -35.846751212231176 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -35.846751212231176.
+[I 2025-12-17 13:12:14,139] Trial 2 finished with value: -132.70806501421575 and parameters: {'embedding_dim': 68, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 1 with value: -35.846751212231176.
+[I 2025-12-17 13:12:17,618] Trial 3 finished with value: -47.61611075064128 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 1 with value: -35.846751212231176.
+[I 2025-12-17 13:12:22,766] Trial 4 finished with value: -7.454839914353274 and parameters: {'embedding_dim': 70, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -7.454839914353274.
+[I 2025-12-17 13:12:29,510] Trial 5 finished with value: -42.682060932360045 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 4 with value: -7.454839914353274.
+[I 2025-12-17 13:12:36,063] Trial 6 finished with value: -114.04455856392626 and parameters: {'embedding_dim': 120, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 4 with value: -7.454839914353274.
+[I 2025-12-17 13:12:42,793] Trial 7 finished with value: -28.615650823466645 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 4 with value: -7.454839914353274.
+[I 2025-12-17 13:12:49,989] Trial 8 finished with value: -8.857007630671955 and parameters: {'embedding_dim': 67, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -7.454839914353274.
+[I 2025-12-17 13:12:53,460] Trial 9 finished with value: -260.567333626546 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 4 with value: -7.454839914353274.
+[I 2025-12-17 13:12:58,511] Trial 10 finished with value: -166.05605712412353 and parameters: {'embedding_dim': 88, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -7.454839914353274.
+[I 2025-12-17 13:13:03,534] Trial 11 finished with value: -80.34165442994153 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -7.454839914353274.
+[I 2025-12-17 13:13:08,884] Trial 12 finished with value: -78.25029007281096 and parameters: {'embedding_dim': 80, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -7.454839914353274.
+[I 2025-12-17 13:13:14,237] Trial 13 finished with value: -23.245070264159708 and parameters: {'embedding_dim': 126, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -7.454839914353274.
+[I 2025-12-17 13:13:21,028] Trial 14 finished with value: -132.4044362751124 and parameters: {'embedding_dim': 73, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 4 with value: -7.454839914353274.
+[I 2025-12-17 13:13:26,113] Trial 15 finished with value: -174.00876769546522 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -7.454839914353274.
+[I 2025-12-17 13:13:33,390] Trial 16 finished with value: -70.61814689520975 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -7.454839914353274.
+[I 2025-12-17 13:13:36,729] Trial 17 finished with value: -177.87096146050646 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 4 with value: -7.454839914353274.
+[I 2025-12-17 13:13:42,072] Trial 18 finished with value: -18.07824272407339 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -7.454839914353274.
+[I 2025-12-17 13:13:48,577] Trial 19 finished with value: -20.70361884768787 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 4 with value: -7.454839914353274.
+[I 2025-12-17 13:13:53,920] Trial 20 finished with value: -22.598991940031432 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -7.454839914353274.
+[I 2025-12-17 13:13:59,339] Trial 21 finished with value: -27.909881111946667 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -7.454839914353274.
+[I 2025-12-17 13:14:05,022] Trial 22 finished with value: -6.223176200590712 and parameters: {'embedding_dim': 72, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:14:10,413] Trial 23 finished with value: -144.04887979808308 and parameters: {'embedding_dim': 70, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:14:13,894] Trial 24 finished with value: -120.25168380594673 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:14:18,934] Trial 25 finished with value: -33.38890893286935 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:14:26,301] Trial 26 finished with value: -62.85350413006152 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:14:31,821] Trial 27 finished with value: -23.498478376749595 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:14:36,747] Trial 28 finished with value: -52.732243521393116 and parameters: {'embedding_dim': 90, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:14:40,261] Trial 29 finished with value: -522.8604091333732 and parameters: {'embedding_dim': 68, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:14:47,606] Trial 30 finished with value: -84.90806144190884 and parameters: {'embedding_dim': 71, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:14:53,115] Trial 31 finished with value: -21.250506945888773 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:14:58,466] Trial 32 finished with value: -37.32143018811486 and parameters: {'embedding_dim': 68, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:15:03,808] Trial 33 finished with value: -37.661019076803086 and parameters: {'embedding_dim': 80, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:15:09,135] Trial 34 finished with value: -46.1269191710778 and parameters: {'embedding_dim': 68, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:15:14,060] Trial 35 finished with value: -39.535949284618724 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:15:17,806] Trial 36 finished with value: -780.7884761611498 and parameters: {'embedding_dim': 70, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:15:22,775] Trial 37 finished with value: -22.386394988645172 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:15:30,044] Trial 38 finished with value: -53.13372557706943 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:15:35,136] Trial 39 finished with value: -160.58280147766177 and parameters: {'embedding_dim': 73, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:15:42,326] Trial 40 finished with value: -91.68235430477448 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:15:48,836] Trial 41 finished with value: -47.1870360699384 and parameters: {'embedding_dim': 66, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:15:55,392] Trial 42 finished with value: -126.61529297609519 and parameters: {'embedding_dim': 71, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:16:01,939] Trial 43 finished with value: -8.313483978528833 and parameters: {'embedding_dim': 66, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:16:08,462] Trial 44 finished with value: -250.5768133859568 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:16:13,411] Trial 45 finished with value: -246.86107596698855 and parameters: {'embedding_dim': 110, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:16:20,307] Trial 46 finished with value: -47.67354952311384 and parameters: {'embedding_dim': 66, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:16:25,606] Trial 47 finished with value: -41.30304460627281 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:16:32,195] Trial 48 finished with value: -83.35548294050159 and parameters: {'embedding_dim': 73, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:16:37,747] Trial 49 finished with value: -45.28760819351347 and parameters: {'embedding_dim': 67, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 22 with value: -6.223176200590712.
+[I 2025-12-17 13:16:43,583] A new study created in memory with name: no-name-bb8bc151-3063-4e0b-993c-9c554446b059
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_7000_1_daejeon_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_7000_1_daejeon_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan7000_1_daejeon.csv: Class 0=5597 | Class 1=6741
+Saved ../../data/data_oversampled/ctgan7000/ctgan7000_1_daejeon.csv: Class 0=5597 | Class 1=6741 | Class 2=15441
+Processing ../../data/data_for_modeling/gwangju_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/gwangju_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-17 13:16:54,716] Trial 0 finished with value: -1390.561691637669 and parameters: {'embedding_dim': 175, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 0 with value: -1390.561691637669.
+[I 2025-12-17 13:18:05,643] Trial 1 finished with value: -805.9554605159901 and parameters: {'embedding_dim': 431, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 1 with value: -805.9554605159901.
+[I 2025-12-17 13:18:20,137] Trial 2 finished with value: -862.2545309000618 and parameters: {'embedding_dim': 174, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 1 with value: -805.9554605159901.
+[I 2025-12-17 13:19:07,167] Trial 3 finished with value: -1324.7640448078357 and parameters: {'embedding_dim': 277, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -805.9554605159901.
+[I 2025-12-17 13:19:50,067] Trial 4 finished with value: -989.9235762393762 and parameters: {'embedding_dim': 234, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 1 with value: -805.9554605159901.
+[I 2025-12-17 13:20:24,804] Trial 5 finished with value: -744.9612859743063 and parameters: {'embedding_dim': 234, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -744.9612859743063.
+[I 2025-12-17 13:20:33,327] Trial 6 finished with value: -7484.286309749936 and parameters: {'embedding_dim': 283, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 5 with value: -744.9612859743063.
+[I 2025-12-17 13:20:48,474] Trial 7 finished with value: -321.4246270144987 and parameters: {'embedding_dim': 247, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 7 with value: -321.4246270144987.
+[I 2025-12-17 13:21:17,434] Trial 8 finished with value: -450.8696708866775 and parameters: {'embedding_dim': 427, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 7 with value: -321.4246270144987.
+[I 2025-12-17 13:22:13,675] Trial 9 finished with value: -735.326125068229 and parameters: {'embedding_dim': 175, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 7 with value: -321.4246270144987.
+[I 2025-12-17 13:22:35,284] Trial 10 finished with value: -770.1667279881376 and parameters: {'embedding_dim': 357, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 7 with value: -321.4246270144987.
+[I 2025-12-17 13:22:57,359] Trial 11 finished with value: -199.18160503423582 and parameters: {'embedding_dim': 498, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 11 with value: -199.18160503423582.
+[I 2025-12-17 13:23:18,898] Trial 12 finished with value: -346.86775934699335 and parameters: {'embedding_dim': 479, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 11 with value: -199.18160503423582.
+[I 2025-12-17 13:23:34,339] Trial 13 finished with value: -421.41180284603763 and parameters: {'embedding_dim': 357, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 11 with value: -199.18160503423582.
+[I 2025-12-17 13:23:55,608] Trial 14 finished with value: -114.18213989573701 and parameters: {'embedding_dim': 507, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 14 with value: -114.18213989573701.
+[I 2025-12-17 13:24:16,316] Trial 15 finished with value: -435.723172569188 and parameters: {'embedding_dim': 512, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 14 with value: -114.18213989573701.
+[I 2025-12-17 13:24:51,310] Trial 16 finished with value: -189.10319268407056 and parameters: {'embedding_dim': 442, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 14 with value: -114.18213989573701.
+[I 2025-12-17 13:25:29,251] Trial 17 finished with value: -527.3801813061768 and parameters: {'embedding_dim': 452, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 14 with value: -114.18213989573701.
+[I 2025-12-17 13:26:06,086] Trial 18 finished with value: -318.6190378995227 and parameters: {'embedding_dim': 392, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 14 with value: -114.18213989573701.
+[I 2025-12-17 13:26:26,765] Trial 19 finished with value: -353.0951863287295 and parameters: {'embedding_dim': 462, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 14 with value: -114.18213989573701.
+[I 2025-12-17 13:27:14,621] Trial 20 finished with value: -523.4759960030368 and parameters: {'embedding_dim': 392, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 14 with value: -114.18213989573701.
+[I 2025-12-17 13:27:37,401] Trial 21 finished with value: -680.7038502228763 and parameters: {'embedding_dim': 509, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 14 with value: -114.18213989573701.
+[I 2025-12-17 13:28:08,669] Trial 22 finished with value: -401.10949161905194 and parameters: {'embedding_dim': 483, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 14 with value: -114.18213989573701.
+[I 2025-12-17 13:28:30,375] Trial 23 finished with value: -581.9084321042735 and parameters: {'embedding_dim': 413, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 14 with value: -114.18213989573701.
+[I 2025-12-17 13:28:59,414] Trial 24 finished with value: -193.8596057655352 and parameters: {'embedding_dim': 483, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 14 with value: -114.18213989573701.
+[I 2025-12-17 13:29:35,688] Trial 25 finished with value: -359.86069182490303 and parameters: {'embedding_dim': 451, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 14 with value: -114.18213989573701.
+[I 2025-12-17 13:30:06,715] Trial 26 finished with value: -25.247128265834668 and parameters: {'embedding_dim': 349, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 26 with value: -25.247128265834668.
+[I 2025-12-17 13:30:41,621] Trial 27 finished with value: -643.8131460242248 and parameters: {'embedding_dim': 344, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 26 with value: -25.247128265834668.
+[I 2025-12-17 13:31:30,926] Trial 28 finished with value: -1438.1681620629329 and parameters: {'embedding_dim': 324, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 26 with value: -25.247128265834668.
+[I 2025-12-17 13:31:46,547] Trial 29 finished with value: -1365.13430212702 and parameters: {'embedding_dim': 391, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 26 with value: -25.247128265834668.
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_7000_1_gwangju_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_7000_1_gwangju_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan7000_1_gwangju.csv: Class 0=6274 | Class 1=6730
+Saved ../../data/data_oversampled/ctgan7000/ctgan7000_1_gwangju.csv: Class 0=6274 | Class 1=6730 | Class 2=15692
+
+Running ctgan_sample_7000_2.py...
+[I 2025-12-17 13:32:19,553] A new study created in memory with name: no-name-25601cbd-7250-4c92-a123-50dcc5f7d683
+[I 2025-12-17 13:32:31,442] Trial 0 finished with value: -6.039771501998899 and parameters: {'embedding_dim': 100, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -6.039771501998899.
+[I 2025-12-17 13:32:46,223] Trial 1 finished with value: -28.87713880065418 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -6.039771501998899.
+[I 2025-12-17 13:32:55,979] Trial 2 finished with value: -72.44888217454869 and parameters: {'embedding_dim': 65, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -6.039771501998899.
+[I 2025-12-17 13:33:20,096] Trial 3 finished with value: -179.89305825779442 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -6.039771501998899.
+[I 2025-12-17 13:33:34,684] Trial 4 finished with value: -10.759608446555069 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -6.039771501998899.
+[I 2025-12-17 13:33:49,445] Trial 5 finished with value: -4.2310053234764045 and parameters: {'embedding_dim': 110, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 5 with value: -4.2310053234764045.
+[I 2025-12-17 13:34:23,584] Trial 6 finished with value: -108.21700914636101 and parameters: {'embedding_dim': 101, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 5 with value: -4.2310053234764045.
+[I 2025-12-17 13:34:29,355] Trial 7 finished with value: -44.274290930611045 and parameters: {'embedding_dim': 83, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -4.2310053234764045.
+[I 2025-12-17 13:34:53,326] Trial 8 finished with value: -17.259332513132087 and parameters: {'embedding_dim': 76, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 5 with value: -4.2310053234764045.
+[I 2025-12-17 13:34:57,239] Trial 9 finished with value: -57.47352899473359 and parameters: {'embedding_dim': 110, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 5 with value: -4.2310053234764045.
+[I 2025-12-17 13:35:12,843] Trial 10 finished with value: -58.16585868062887 and parameters: {'embedding_dim': 121, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 5 with value: -4.2310053234764045.
+[I 2025-12-17 13:35:19,447] Trial 11 finished with value: -51.40285582273643 and parameters: {'embedding_dim': 109, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 5 with value: -4.2310053234764045.
+[I 2025-12-17 13:35:30,480] Trial 12 finished with value: -37.54709823983908 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 5 with value: -4.2310053234764045.
+[I 2025-12-17 13:35:37,072] Trial 13 finished with value: -116.76055430171745 and parameters: {'embedding_dim': 111, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 5 with value: -4.2310053234764045.
+[I 2025-12-17 13:35:47,098] Trial 14 finished with value: -1.4231361318656623 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:36:04,648] Trial 15 finished with value: -63.96704293539972 and parameters: {'embedding_dim': 118, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:36:18,076] Trial 16 finished with value: -46.67832124379861 and parameters: {'embedding_dim': 89, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:36:41,167] Trial 17 finished with value: -16.81750503281018 and parameters: {'embedding_dim': 105, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:36:47,751] Trial 18 finished with value: -42.31883073484536 and parameters: {'embedding_dim': 119, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:36:53,543] Trial 19 finished with value: -22.527718628428726 and parameters: {'embedding_dim': 128, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:37:07,052] Trial 20 finished with value: -16.816141762469385 and parameters: {'embedding_dim': 87, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:37:17,107] Trial 21 finished with value: -289.8393897351886 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:37:27,187] Trial 22 finished with value: -55.27377466820539 and parameters: {'embedding_dim': 100, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:37:37,356] Trial 23 finished with value: -87.49577069329787 and parameters: {'embedding_dim': 114, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:37:43,931] Trial 24 finished with value: -28.190739598103068 and parameters: {'embedding_dim': 105, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:38:06,926] Trial 25 finished with value: -7.201863551441156 and parameters: {'embedding_dim': 105, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:38:20,476] Trial 26 finished with value: -60.87653749748941 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:38:30,542] Trial 27 finished with value: -12.45960578983072 and parameters: {'embedding_dim': 99, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:38:34,438] Trial 28 finished with value: -25.761835491544936 and parameters: {'embedding_dim': 115, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:38:57,602] Trial 29 finished with value: -146.07316272500933 and parameters: {'embedding_dim': 90, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:39:12,329] Trial 30 finished with value: -97.27327375232647 and parameters: {'embedding_dim': 128, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:39:35,173] Trial 31 finished with value: -11.881811672019083 and parameters: {'embedding_dim': 105, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:39:58,663] Trial 32 finished with value: -12.447844351741777 and parameters: {'embedding_dim': 107, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:40:21,745] Trial 33 finished with value: -10.155330178868486 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:40:53,024] Trial 34 finished with value: -84.37964327275387 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:41:16,473] Trial 35 finished with value: -83.59437924690266 and parameters: {'embedding_dim': 113, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:41:24,187] Trial 36 finished with value: -20.056601635268528 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:41:47,256] Trial 37 finished with value: -67.46839622329819 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:41:57,606] Trial 38 finished with value: -17.36471022280484 and parameters: {'embedding_dim': 83, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:42:20,680] Trial 39 finished with value: -4.20267062064582 and parameters: {'embedding_dim': 94, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:42:24,629] Trial 40 finished with value: -2.100573223661184 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:42:28,569] Trial 41 finished with value: -284.8582872261464 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:42:32,467] Trial 42 finished with value: -296.86009874965424 and parameters: {'embedding_dim': 96, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:42:36,360] Trial 43 finished with value: -49.19514050153556 and parameters: {'embedding_dim': 85, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:42:40,480] Trial 44 finished with value: -103.45269268442587 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:42:44,500] Trial 45 finished with value: -27.306271756444218 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:42:51,102] Trial 46 finished with value: -14.894892998398117 and parameters: {'embedding_dim': 96, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:43:14,013] Trial 47 finished with value: -27.9390190690054 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:43:20,557] Trial 48 finished with value: -47.219696829663704 and parameters: {'embedding_dim': 109, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:43:43,395] Trial 49 finished with value: -138.76953780883784 and parameters: {'embedding_dim': 89, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 14 with value: -1.4231361318656623.
+[I 2025-12-17 13:43:53,584] A new study created in memory with name: no-name-e742f6c7-1b46-42b7-857c-8bee19f4141c
+Using device: cuda
+Processing ../../data/data_for_modeling/incheon_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/incheon_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-17 13:44:20,527] Trial 0 finished with value: -872.6802570982177 and parameters: {'embedding_dim': 420, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 0 with value: -872.6802570982177.
+[I 2025-12-17 13:44:58,148] Trial 1 finished with value: -163.24123226592448 and parameters: {'embedding_dim': 395, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 1 with value: -163.24123226592448.
+[I 2025-12-17 13:45:17,803] Trial 2 finished with value: -78.43872091984129 and parameters: {'embedding_dim': 157, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 2 with value: -78.43872091984129.
+[I 2025-12-17 13:45:48,719] Trial 3 finished with value: -242.24473002780516 and parameters: {'embedding_dim': 155, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 2 with value: -78.43872091984129.
+[I 2025-12-17 13:46:38,167] Trial 4 finished with value: -250.62275083564407 and parameters: {'embedding_dim': 276, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -78.43872091984129.
+[I 2025-12-17 13:47:11,290] Trial 5 finished with value: -195.61842650014626 and parameters: {'embedding_dim': 508, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -78.43872091984129.
+[I 2025-12-17 13:47:56,926] Trial 6 finished with value: -195.12640896342148 and parameters: {'embedding_dim': 357, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 2 with value: -78.43872091984129.
+[I 2025-12-17 13:48:28,225] Trial 7 finished with value: -170.71179599561387 and parameters: {'embedding_dim': 152, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 2 with value: -78.43872091984129.
+[I 2025-12-17 13:49:01,834] Trial 8 finished with value: -88.6639652742536 and parameters: {'embedding_dim': 233, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -78.43872091984129.
+[I 2025-12-17 13:50:26,866] Trial 9 finished with value: -254.5220049635309 and parameters: {'embedding_dim': 173, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 2 with value: -78.43872091984129.
+[I 2025-12-17 13:50:55,251] Trial 10 finished with value: -320.6257198636077 and parameters: {'embedding_dim': 274, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 2 with value: -78.43872091984129.
+[I 2025-12-17 13:51:13,928] Trial 11 finished with value: -399.95742362091045 and parameters: {'embedding_dim': 213, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 2 with value: -78.43872091984129.
+[I 2025-12-17 13:51:33,197] Trial 12 finished with value: -8805.55774673739 and parameters: {'embedding_dim': 239, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 2 with value: -78.43872091984129.
+[I 2025-12-17 13:52:22,875] Trial 13 finished with value: -181.30722543429133 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -78.43872091984129.
+[I 2025-12-17 13:52:41,816] Trial 14 finished with value: -540.5528874839849 and parameters: {'embedding_dim': 210, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 2 with value: -78.43872091984129.
+[I 2025-12-17 13:53:31,693] Trial 15 finished with value: -362.31790960660936 and parameters: {'embedding_dim': 277, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -78.43872091984129.
+[I 2025-12-17 13:54:08,674] Trial 16 finished with value: -354.135845797156 and parameters: {'embedding_dim': 337, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 2 with value: -78.43872091984129.
+[I 2025-12-17 13:54:42,341] Trial 17 finished with value: -381.9285065096834 and parameters: {'embedding_dim': 206, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -78.43872091984129.
+[I 2025-12-17 13:55:10,179] Trial 18 finished with value: -109.05685945553495 and parameters: {'embedding_dim': 248, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 2 with value: -78.43872091984129.
+[I 2025-12-17 13:56:17,352] Trial 19 finished with value: -203.3277211328641 and parameters: {'embedding_dim': 184, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -78.43872091984129.
+[I 2025-12-17 13:56:50,688] Trial 20 finished with value: -6063.120498692326 and parameters: {'embedding_dim': 236, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -78.43872091984129.
+[I 2025-12-17 13:57:18,534] Trial 21 finished with value: -58.951125091600574 and parameters: {'embedding_dim': 255, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 21 with value: -58.951125091600574.
+[I 2025-12-17 13:57:47,222] Trial 22 finished with value: -1070.9663262928852 and parameters: {'embedding_dim': 311, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 21 with value: -58.951125091600574.
+[I 2025-12-17 13:58:06,535] Trial 23 finished with value: -834.1967796352857 and parameters: {'embedding_dim': 310, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 21 with value: -58.951125091600574.
+[I 2025-12-17 13:58:35,608] Trial 24 finished with value: -226.10497794004206 and parameters: {'embedding_dim': 135, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 21 with value: -58.951125091600574.
+[I 2025-12-17 13:58:54,315] Trial 25 finished with value: -404.9328128983784 and parameters: {'embedding_dim': 193, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 21 with value: -58.951125091600574.
+[I 2025-12-17 13:59:22,926] Trial 26 finished with value: -2.9447075996645418 and parameters: {'embedding_dim': 254, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 26 with value: -2.9447075996645418.
+[I 2025-12-17 14:00:02,632] Trial 27 finished with value: -78.28694125779285 and parameters: {'embedding_dim': 371, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 26 with value: -2.9447075996645418.
+[I 2025-12-17 14:00:40,898] Trial 28 finished with value: -122.6904291256364 and parameters: {'embedding_dim': 378, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 26 with value: -2.9447075996645418.
+[I 2025-12-17 14:01:06,012] Trial 29 finished with value: -87.71439227806947 and parameters: {'embedding_dim': 462, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 26 with value: -2.9447075996645418.
+[I 2025-12-17 14:01:35,146] A new study created in memory with name: no-name-b5b3b5a6-06a7-4995-891c-9e7d3f061895
+[I 2025-12-17 14:01:38,399] Trial 0 finished with value: -0.30341578823867 and parameters: {'embedding_dim': 91, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:01:43,235] Trial 1 finished with value: -12.110811194096508 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:01:46,406] Trial 2 finished with value: -44.44009833410004 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:01:51,871] Trial 3 finished with value: -17.2801259839506 and parameters: {'embedding_dim': 126, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:01:58,911] Trial 4 finished with value: -0.8850278282119286 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:02:02,322] Trial 5 finished with value: -13.367560558321909 and parameters: {'embedding_dim': 112, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:02:05,681] Trial 6 finished with value: -3.9083136439013098 and parameters: {'embedding_dim': 94, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:02:09,218] Trial 7 finished with value: -171.62137049327916 and parameters: {'embedding_dim': 69, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:02:16,521] Trial 8 finished with value: -26.110745075807 and parameters: {'embedding_dim': 99, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:02:23,334] Trial 9 finished with value: -145.42532989135708 and parameters: {'embedding_dim': 87, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:02:26,532] Trial 10 finished with value: -5.840587380856331 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:02:31,414] Trial 11 finished with value: -53.481369644082804 and parameters: {'embedding_dim': 106, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:02:36,239] Trial 12 finished with value: -343.71619719099044 and parameters: {'embedding_dim': 116, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:02:42,729] Trial 13 finished with value: -95.2782933573919 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:02:47,537] Trial 14 finished with value: -79.67198475026552 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:02:50,760] Trial 15 finished with value: -100.78686086702763 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:02:57,214] Trial 16 finished with value: -73.18386376175647 and parameters: {'embedding_dim': 116, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:03:02,019] Trial 17 finished with value: -26.75879315007704 and parameters: {'embedding_dim': 91, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:03:05,495] Trial 18 finished with value: -93.30353700604942 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:03:10,518] Trial 19 finished with value: -48.625142719196475 and parameters: {'embedding_dim': 127, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:03:16,963] Trial 20 finished with value: -56.71988376189631 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:03:21,854] Trial 21 finished with value: -133.683452657111 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:03:25,420] Trial 22 finished with value: -132.81241238476184 and parameters: {'embedding_dim': 109, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:03:28,718] Trial 23 finished with value: -113.38525924049172 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:03:32,076] Trial 24 finished with value: -337.21412601629703 and parameters: {'embedding_dim': 91, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:03:35,473] Trial 25 finished with value: -172.8245381230863 and parameters: {'embedding_dim': 84, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:03:40,468] Trial 26 finished with value: -1.9200563699810547 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:03:48,900] Trial 27 finished with value: -74.98004499786788 and parameters: {'embedding_dim': 101, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:03:55,543] Trial 28 finished with value: -18.764131038927886 and parameters: {'embedding_dim': 115, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:04:00,470] Trial 29 finished with value: -58.12737184202003 and parameters: {'embedding_dim': 109, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:04:05,310] Trial 30 finished with value: -7.695447111839662 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:04:10,197] Trial 31 finished with value: -189.29438404392292 and parameters: {'embedding_dim': 94, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:04:13,409] Trial 32 finished with value: -303.4010931916707 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -0.30341578823867.
+[I 2025-12-17 14:04:16,853] Trial 33 finished with value: -0.030829043253997865 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 33 with value: -0.030829043253997865.
+[I 2025-12-17 14:04:20,283] Trial 34 finished with value: -81.50543005344309 and parameters: {'embedding_dim': 120, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 33 with value: -0.030829043253997865.
+[I 2025-12-17 14:04:25,572] Trial 35 finished with value: -139.97862382968373 and parameters: {'embedding_dim': 108, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 33 with value: -0.030829043253997865.
+[I 2025-12-17 14:04:31,809] Trial 36 finished with value: -69.72999242739795 and parameters: {'embedding_dim': 100, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 33 with value: -0.030829043253997865.
+[I 2025-12-17 14:04:36,813] Trial 37 finished with value: -52.23516318877221 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 33 with value: -0.030829043253997865.
+[I 2025-12-17 14:04:44,086] Trial 38 finished with value: -69.74413822087394 and parameters: {'embedding_dim': 103, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 33 with value: -0.030829043253997865.
+[I 2025-12-17 14:04:47,521] Trial 39 finished with value: -71.13481068643307 and parameters: {'embedding_dim': 123, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 33 with value: -0.030829043253997865.
+[I 2025-12-17 14:04:52,404] Trial 40 finished with value: -75.84577375745926 and parameters: {'embedding_dim': 112, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 33 with value: -0.030829043253997865.
+[I 2025-12-17 14:04:55,798] Trial 41 finished with value: -17.74938379560531 and parameters: {'embedding_dim': 95, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 33 with value: -0.030829043253997865.
+[I 2025-12-17 14:04:59,097] Trial 42 finished with value: -17.37696098367415 and parameters: {'embedding_dim': 99, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 33 with value: -0.030829043253997865.
+[I 2025-12-17 14:05:02,400] Trial 43 finished with value: -65.45568593862211 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 33 with value: -0.030829043253997865.
+[I 2025-12-17 14:05:05,578] Trial 44 finished with value: -176.39682602407956 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 33 with value: -0.030829043253997865.
+[I 2025-12-17 14:05:09,669] Trial 45 finished with value: -41.336477167011566 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 33 with value: -0.030829043253997865.
+[I 2025-12-17 14:05:18,670] Trial 46 finished with value: -76.89188552021584 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 33 with value: -0.030829043253997865.
+[I 2025-12-17 14:05:23,712] Trial 47 finished with value: -53.62613316029633 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 33 with value: -0.030829043253997865.
+[I 2025-12-17 14:05:27,030] Trial 48 finished with value: -64.95804410833989 and parameters: {'embedding_dim': 66, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 33 with value: -0.030829043253997865.
+[I 2025-12-17 14:05:33,917] Trial 49 finished with value: -52.61933320226266 and parameters: {'embedding_dim': 87, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 33 with value: -0.030829043253997865.
+[I 2025-12-17 14:05:38,512] A new study created in memory with name: no-name-6725d502-25b6-46d6-a746-7945782ec1fa
+[I 2025-12-17 14:05:51,913] Trial 0 finished with value: -250.11833346518802 and parameters: {'embedding_dim': 132, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 0 with value: -250.11833346518802.
+[I 2025-12-17 14:06:37,535] Trial 1 finished with value: -596.7383578330042 and parameters: {'embedding_dim': 278, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -250.11833346518802.
+[I 2025-12-17 14:06:53,089] Trial 2 finished with value: -986.4509429065641 and parameters: {'embedding_dim': 170, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 0 with value: -250.11833346518802.
+[I 2025-12-17 14:07:12,884] Trial 3 finished with value: -568.7638830979699 and parameters: {'embedding_dim': 434, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 0 with value: -250.11833346518802.
+[I 2025-12-17 14:08:13,508] Trial 4 finished with value: -419.6931055133325 and parameters: {'embedding_dim': 328, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 0 with value: -250.11833346518802.
+[I 2025-12-17 14:08:33,356] Trial 5 finished with value: -225.69976367887594 and parameters: {'embedding_dim': 396, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 5 with value: -225.69976367887594.
+[I 2025-12-17 14:08:54,564] Trial 6 finished with value: -391.0933148618638 and parameters: {'embedding_dim': 345, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 5 with value: -225.69976367887594.
+[I 2025-12-17 14:09:55,105] Trial 7 finished with value: -335.6190087226484 and parameters: {'embedding_dim': 142, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 5 with value: -225.69976367887594.
+[I 2025-12-17 14:10:06,578] Trial 8 finished with value: -577.5919726633979 and parameters: {'embedding_dim': 505, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 5 with value: -225.69976367887594.
+[I 2025-12-17 14:10:17,649] Trial 9 finished with value: -5199.45769741414 and parameters: {'embedding_dim': 341, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 5 with value: -225.69976367887594.
+[I 2025-12-17 14:10:54,375] Trial 10 finished with value: -102.31729532069738 and parameters: {'embedding_dim': 424, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 10 with value: -102.31729532069738.
+[I 2025-12-17 14:11:31,946] Trial 11 finished with value: -657.7882691515532 and parameters: {'embedding_dim': 427, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 10 with value: -102.31729532069738.
+[I 2025-12-17 14:12:14,855] Trial 12 finished with value: -226.51352238347783 and parameters: {'embedding_dim': 419, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 10 with value: -102.31729532069738.
+[I 2025-12-17 14:12:50,898] Trial 13 finished with value: -151.7121846657423 and parameters: {'embedding_dim': 512, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 10 with value: -102.31729532069738.
+[I 2025-12-17 14:13:05,766] Trial 14 finished with value: -858.8617939736623 and parameters: {'embedding_dim': 498, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 10 with value: -102.31729532069738.
+[I 2025-12-17 14:13:41,557] Trial 15 finished with value: -199.5283487362176 and parameters: {'embedding_dim': 469, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 10 with value: -102.31729532069738.
+[I 2025-12-17 14:14:11,749] Trial 16 finished with value: -63.719622692716285 and parameters: {'embedding_dim': 254, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 16 with value: -63.719622692716285.
+[I 2025-12-17 14:14:41,390] Trial 17 finished with value: -69.94241260714703 and parameters: {'embedding_dim': 251, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 16 with value: -63.719622692716285.
+[I 2025-12-17 14:15:12,390] Trial 18 finished with value: -262.1346139901135 and parameters: {'embedding_dim': 230, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 16 with value: -63.719622692716285.
+[I 2025-12-17 14:15:35,681] Trial 19 finished with value: -165.56700567021824 and parameters: {'embedding_dim': 244, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 16 with value: -63.719622692716285.
+[I 2025-12-17 14:15:51,008] Trial 20 finished with value: -228.6842509063712 and parameters: {'embedding_dim': 201, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 16 with value: -63.719622692716285.
+[I 2025-12-17 14:16:21,402] Trial 21 finished with value: -104.8153160692727 and parameters: {'embedding_dim': 281, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 16 with value: -63.719622692716285.
+[I 2025-12-17 14:16:49,072] Trial 22 finished with value: -167.43902442057788 and parameters: {'embedding_dim': 284, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 16 with value: -63.719622692716285.
+[I 2025-12-17 14:17:17,885] Trial 23 finished with value: -197.0485274201696 and parameters: {'embedding_dim': 370, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 16 with value: -63.719622692716285.
+[I 2025-12-17 14:17:56,701] Trial 24 finished with value: -61.14575361369437 and parameters: {'embedding_dim': 214, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 24 with value: -61.14575361369437.
+[I 2025-12-17 14:18:27,210] Trial 25 finished with value: -79.33922270320255 and parameters: {'embedding_dim': 207, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 24 with value: -61.14575361369437.
+[I 2025-12-17 14:19:03,445] Trial 26 finished with value: -613.9670529335856 and parameters: {'embedding_dim': 249, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -61.14575361369437.
+[I 2025-12-17 14:19:38,521] Trial 27 finished with value: -483.1408211406212 and parameters: {'embedding_dim': 295, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 24 with value: -61.14575361369437.
+[I 2025-12-17 14:20:07,151] Trial 28 finished with value: -41.30578185681668 and parameters: {'embedding_dim': 182, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 28 with value: -41.30578185681668.
+[I 2025-12-17 14:20:28,312] Trial 29 finished with value: -107.06900305922073 and parameters: {'embedding_dim': 136, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 28 with value: -41.30578185681668.
+[I 2025-12-17 14:20:56,523] A new study created in memory with name: no-name-b4948e45-101f-4c4d-946e-9aed2a879326
+[I 2025-12-17 14:21:01,580] Trial 0 finished with value: -15.639070818440524 and parameters: {'embedding_dim': 84, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -15.639070818440524.
+[I 2025-12-17 14:21:08,084] Trial 1 finished with value: -26.37640675347026 and parameters: {'embedding_dim': 113, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -15.639070818440524.
+[I 2025-12-17 14:21:14,893] Trial 2 finished with value: -86.87005461685197 and parameters: {'embedding_dim': 96, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -15.639070818440524.
+[I 2025-12-17 14:21:20,266] Trial 3 finished with value: -16.27547365314236 and parameters: {'embedding_dim': 97, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -15.639070818440524.
+[I 2025-12-17 14:21:25,168] Trial 4 finished with value: -51.200307728193216 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -15.639070818440524.
+[I 2025-12-17 14:21:30,166] Trial 5 finished with value: -23.46244885374338 and parameters: {'embedding_dim': 124, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -15.639070818440524.
+[I 2025-12-17 14:21:36,518] Trial 6 finished with value: -24.821670902422664 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -15.639070818440524.
+[I 2025-12-17 14:21:40,199] Trial 7 finished with value: -13.39424955035504 and parameters: {'embedding_dim': 94, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -13.39424955035504.
+[I 2025-12-17 14:21:43,680] Trial 8 finished with value: -80.21710125688647 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -13.39424955035504.
+[I 2025-12-17 14:21:49,009] Trial 9 finished with value: -15.976906073538409 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 7 with value: -13.39424955035504.
+[I 2025-12-17 14:21:52,576] Trial 10 finished with value: -15.270386310236287 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -13.39424955035504.
+[I 2025-12-17 14:21:56,025] Trial 11 finished with value: -156.95456736800452 and parameters: {'embedding_dim': 65, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -13.39424955035504.
+[I 2025-12-17 14:21:59,511] Trial 12 finished with value: -478.3178827964135 and parameters: {'embedding_dim': 65, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -13.39424955035504.
+[I 2025-12-17 14:22:03,060] Trial 13 finished with value: -87.39237394327597 and parameters: {'embedding_dim': 75, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -13.39424955035504.
+[I 2025-12-17 14:22:06,665] Trial 14 finished with value: -118.22432375025497 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -13.39424955035504.
+[I 2025-12-17 14:22:10,341] Trial 15 finished with value: -54.67746304568389 and parameters: {'embedding_dim': 109, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -13.39424955035504.
+[I 2025-12-17 14:22:13,629] Trial 16 finished with value: -157.53939210944236 and parameters: {'embedding_dim': 127, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 7 with value: -13.39424955035504.
+[I 2025-12-17 14:22:17,080] Trial 17 finished with value: -53.87937610441519 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -13.39424955035504.
+[I 2025-12-17 14:22:20,661] Trial 18 finished with value: -44.07630202685088 and parameters: {'embedding_dim': 117, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -13.39424955035504.
+[I 2025-12-17 14:22:25,667] Trial 19 finished with value: -40.802573727082105 and parameters: {'embedding_dim': 102, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 7 with value: -13.39424955035504.
+[I 2025-12-17 14:22:29,137] Trial 20 finished with value: -7.290011995965833 and parameters: {'embedding_dim': 87, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 20 with value: -7.290011995965833.
+[I 2025-12-17 14:22:32,586] Trial 21 finished with value: -5.329193999007046 and parameters: {'embedding_dim': 87, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:22:36,047] Trial 22 finished with value: -123.68154350079847 and parameters: {'embedding_dim': 88, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:22:39,526] Trial 23 finished with value: -291.69475645445726 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:22:42,986] Trial 24 finished with value: -123.7672973827118 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:22:48,336] Trial 25 finished with value: -211.59651578739297 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:22:51,794] Trial 26 finished with value: -239.61061123414123 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:22:55,266] Trial 27 finished with value: -275.2737717228309 and parameters: {'embedding_dim': 85, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:23:00,280] Trial 28 finished with value: -25.602023876952426 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:23:05,149] Trial 29 finished with value: -258.16242138306893 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:23:08,451] Trial 30 finished with value: -39.18674940495131 and parameters: {'embedding_dim': 85, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:23:11,956] Trial 31 finished with value: -71.29513837005382 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:23:15,442] Trial 32 finished with value: -22.65012591964783 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:23:18,908] Trial 33 finished with value: -72.0128739115105 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:23:26,163] Trial 34 finished with value: -79.67532484549363 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:23:29,637] Trial 35 finished with value: -12.197547643270262 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:23:32,936] Trial 36 finished with value: -21.390056303411974 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:23:37,855] Trial 37 finished with value: -48.33534326656006 and parameters: {'embedding_dim': 94, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:23:45,292] Trial 38 finished with value: -65.56146489635917 and parameters: {'embedding_dim': 84, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:23:48,725] Trial 39 finished with value: -56.56858598200838 and parameters: {'embedding_dim': 109, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:23:54,135] Trial 40 finished with value: -81.87374229561942 and parameters: {'embedding_dim': 88, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:23:57,868] Trial 41 finished with value: -46.97385323241646 and parameters: {'embedding_dim': 99, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:24:01,358] Trial 42 finished with value: -16.978522870860452 and parameters: {'embedding_dim': 94, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:24:04,873] Trial 43 finished with value: -73.28482040505975 and parameters: {'embedding_dim': 116, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:24:08,351] Trial 44 finished with value: -36.60155614106208 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:24:11,851] Trial 45 finished with value: -42.42474227807317 and parameters: {'embedding_dim': 91, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:24:15,543] Trial 46 finished with value: -78.49797935580219 and parameters: {'embedding_dim': 105, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:24:19,162] Trial 47 finished with value: -5.412718058463285 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:24:22,511] Trial 48 finished with value: -218.92699427242883 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:24:26,037] Trial 49 finished with value: -70.13503067489883 and parameters: {'embedding_dim': 68, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 21 with value: -5.329193999007046.
+[I 2025-12-17 14:24:29,796] A new study created in memory with name: no-name-7de0db63-a0e6-418d-899f-bae5e85b806a
+[I 2025-12-17 14:24:37,529] Trial 0 finished with value: -1012.2225997933912 and parameters: {'embedding_dim': 363, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 0 with value: -1012.2225997933912.
+[I 2025-12-17 14:24:55,464] Trial 1 finished with value: -959.0787752110878 and parameters: {'embedding_dim': 447, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 1 with value: -959.0787752110878.
+[I 2025-12-17 14:25:04,621] Trial 2 finished with value: -3765.631031504158 and parameters: {'embedding_dim': 396, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 1 with value: -959.0787752110878.
+[I 2025-12-17 14:25:39,521] Trial 3 finished with value: -2095.199291790879 and parameters: {'embedding_dim': 358, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 1 with value: -959.0787752110878.
+[I 2025-12-17 14:26:15,000] Trial 4 finished with value: -389.81463924694185 and parameters: {'embedding_dim': 446, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 4 with value: -389.81463924694185.
+[I 2025-12-17 14:26:44,966] Trial 5 finished with value: -649.3554222801743 and parameters: {'embedding_dim': 492, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 4 with value: -389.81463924694185.
+[I 2025-12-17 14:27:02,677] Trial 6 finished with value: -1584.6329353721394 and parameters: {'embedding_dim': 158, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 4 with value: -389.81463924694185.
+[I 2025-12-17 14:27:17,597] Trial 7 finished with value: -607.6626235889372 and parameters: {'embedding_dim': 246, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 4 with value: -389.81463924694185.
+[I 2025-12-17 14:27:29,181] Trial 8 finished with value: -716.5642001836563 and parameters: {'embedding_dim': 419, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 4 with value: -389.81463924694185.
+[I 2025-12-17 14:27:36,796] Trial 9 finished with value: -2625.116739615375 and parameters: {'embedding_dim': 263, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 4 with value: -389.81463924694185.
+[I 2025-12-17 14:28:00,634] Trial 10 finished with value: -1385.5877522320093 and parameters: {'embedding_dim': 488, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -389.81463924694185.
+[I 2025-12-17 14:28:13,833] Trial 11 finished with value: -468.8282957001685 and parameters: {'embedding_dim': 261, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 4 with value: -389.81463924694185.
+[I 2025-12-17 14:28:42,961] Trial 12 finished with value: -438.9197500746797 and parameters: {'embedding_dim': 273, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 4 with value: -389.81463924694185.
+[I 2025-12-17 14:29:11,934] Trial 13 finished with value: -620.8150812902904 and parameters: {'embedding_dim': 306, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 4 with value: -389.81463924694185.
+[I 2025-12-17 14:29:41,290] Trial 14 finished with value: -176.0501896478027 and parameters: {'embedding_dim': 165, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 14 with value: -176.0501896478027.
+[I 2025-12-17 14:30:11,124] Trial 15 finished with value: -130.99143578910756 and parameters: {'embedding_dim': 133, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 15 with value: -130.99143578910756.
+[I 2025-12-17 14:30:35,484] Trial 16 finished with value: -1146.5402923489978 and parameters: {'embedding_dim': 141, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -130.99143578910756.
+[I 2025-12-17 14:30:53,369] Trial 17 finished with value: -465.74229382733046 and parameters: {'embedding_dim': 191, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -130.99143578910756.
+[I 2025-12-17 14:31:22,059] Trial 18 finished with value: -224.9042840347794 and parameters: {'embedding_dim': 198, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 15 with value: -130.99143578910756.
+[I 2025-12-17 14:31:39,640] Trial 19 finished with value: -1283.3203983867845 and parameters: {'embedding_dim': 129, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -130.99143578910756.
+[I 2025-12-17 14:32:03,467] Trial 20 finished with value: -459.15212867811533 and parameters: {'embedding_dim': 200, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -130.99143578910756.
+[I 2025-12-17 14:32:32,441] Trial 21 finished with value: -205.4527187571726 and parameters: {'embedding_dim': 197, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 15 with value: -130.99143578910756.
+[I 2025-12-17 14:33:01,698] Trial 22 finished with value: -1383.6381419233703 and parameters: {'embedding_dim': 168, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 15 with value: -130.99143578910756.
+[I 2025-12-17 14:33:31,198] Trial 23 finished with value: -146.09870889424326 and parameters: {'embedding_dim': 228, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 15 with value: -130.99143578910756.
+[I 2025-12-17 14:33:59,939] Trial 24 finished with value: -335.9457654396321 and parameters: {'embedding_dim': 232, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 15 with value: -130.99143578910756.
+[I 2025-12-17 14:34:23,782] Trial 25 finished with value: -512.2763530111807 and parameters: {'embedding_dim': 222, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -130.99143578910756.
+[I 2025-12-17 14:34:47,381] Trial 26 finished with value: -619.1412507737698 and parameters: {'embedding_dim': 167, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -130.99143578910756.
+[I 2025-12-17 14:35:16,997] Trial 27 finished with value: -342.5802730433215 and parameters: {'embedding_dim': 302, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 15 with value: -130.99143578910756.
+[I 2025-12-17 14:35:35,955] Trial 28 finished with value: -517.962895982157 and parameters: {'embedding_dim': 160, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 15 with value: -130.99143578910756.
+[I 2025-12-17 14:35:49,145] Trial 29 finished with value: -596.7626213745635 and parameters: {'embedding_dim': 348, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 15 with value: -130.99143578910756.
+[I 2025-12-17 14:36:18,850] A new study created in memory with name: no-name-3b58680c-b8b4-41c7-af5d-9ccf81b65f93
+[I 2025-12-17 14:36:22,224] Trial 0 finished with value: -312.9851780031683 and parameters: {'embedding_dim': 121, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -312.9851780031683.
+[I 2025-12-17 14:36:29,283] Trial 1 finished with value: -29.78665838998119 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -29.78665838998119.
+[I 2025-12-17 14:36:34,029] Trial 2 finished with value: -10.18481756096566 and parameters: {'embedding_dim': 75, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -10.18481756096566.
+[I 2025-12-17 14:36:38,816] Trial 3 finished with value: -62.041617961962025 and parameters: {'embedding_dim': 77, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -10.18481756096566.
+[I 2025-12-17 14:36:45,892] Trial 4 finished with value: -72.42009598356574 and parameters: {'embedding_dim': 115, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -10.18481756096566.
+[I 2025-12-17 14:36:49,114] Trial 5 finished with value: -114.09798269216232 and parameters: {'embedding_dim': 96, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -10.18481756096566.
+[I 2025-12-17 14:36:55,544] Trial 6 finished with value: -20.46540399321287 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -10.18481756096566.
+[I 2025-12-17 14:37:00,390] Trial 7 finished with value: -28.35873672214006 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -10.18481756096566.
+[I 2025-12-17 14:37:07,567] Trial 8 finished with value: -15.7706564276981 and parameters: {'embedding_dim': 91, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -10.18481756096566.
+[I 2025-12-17 14:37:10,799] Trial 9 finished with value: -30.153159585948593 and parameters: {'embedding_dim': 106, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -10.18481756096566.
+[I 2025-12-17 14:37:15,632] Trial 10 finished with value: -74.7352237972808 and parameters: {'embedding_dim': 65, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -10.18481756096566.
+[I 2025-12-17 14:37:21,068] Trial 11 finished with value: -62.05308828367134 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -10.18481756096566.
+[I 2025-12-17 14:37:27,438] Trial 12 finished with value: -260.5441830778105 and parameters: {'embedding_dim': 67, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -10.18481756096566.
+[I 2025-12-17 14:37:32,674] Trial 13 finished with value: -32.431904427971716 and parameters: {'embedding_dim': 90, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -10.18481756096566.
+[I 2025-12-17 14:37:39,273] Trial 14 finished with value: -64.09673679960179 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -10.18481756096566.
+[I 2025-12-17 14:37:44,036] Trial 15 finished with value: -42.83728311779916 and parameters: {'embedding_dim': 86, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -10.18481756096566.
+[I 2025-12-17 14:37:51,088] Trial 16 finished with value: -48.621218072901996 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -10.18481756096566.
+[I 2025-12-17 14:37:54,219] Trial 17 finished with value: -53.4059030316773 and parameters: {'embedding_dim': 95, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 2 with value: -10.18481756096566.
+[I 2025-12-17 14:37:59,426] Trial 18 finished with value: -61.11705350074029 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -10.18481756096566.
+[I 2025-12-17 14:38:06,077] Trial 19 finished with value: -14.079387445558583 and parameters: {'embedding_dim': 95, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -10.18481756096566.
+[I 2025-12-17 14:38:11,116] Trial 20 finished with value: -0.537647277081665 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:38:16,077] Trial 21 finished with value: -58.64767469556867 and parameters: {'embedding_dim': 127, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:38:21,040] Trial 22 finished with value: -21.22341952201368 and parameters: {'embedding_dim': 115, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:38:26,012] Trial 23 finished with value: -49.75770503355768 and parameters: {'embedding_dim': 110, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:38:29,246] Trial 24 finished with value: -86.4421146739201 and parameters: {'embedding_dim': 98, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:38:34,217] Trial 25 finished with value: -90.2844608823995 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:38:39,148] Trial 26 finished with value: -95.77286248555504 and parameters: {'embedding_dim': 71, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:38:45,804] Trial 27 finished with value: -97.38912533528615 and parameters: {'embedding_dim': 101, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:38:52,478] Trial 28 finished with value: -81.05047195290473 and parameters: {'embedding_dim': 112, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:38:55,679] Trial 29 finished with value: -117.60077158958424 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:39:00,633] Trial 30 finished with value: -213.71049422294254 and parameters: {'embedding_dim': 122, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:39:07,687] Trial 31 finished with value: -13.43814930813372 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:39:14,880] Trial 32 finished with value: -3.639792032929612 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:39:21,993] Trial 33 finished with value: -20.53320527136011 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:39:29,063] Trial 34 finished with value: -9.177965735898642 and parameters: {'embedding_dim': 90, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:39:34,290] Trial 35 finished with value: -124.60401316205751 and parameters: {'embedding_dim': 87, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:39:41,313] Trial 36 finished with value: -1.0526388648146656 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:39:48,530] Trial 37 finished with value: -30.346257397277558 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:39:55,682] Trial 38 finished with value: -26.056969663860194 and parameters: {'embedding_dim': 83, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:40:02,767] Trial 39 finished with value: -15.215978240496675 and parameters: {'embedding_dim': 99, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:40:09,866] Trial 40 finished with value: -31.00756425170437 and parameters: {'embedding_dim': 90, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:40:16,948] Trial 41 finished with value: -41.86748397130763 and parameters: {'embedding_dim': 75, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:40:21,693] Trial 42 finished with value: -25.666333650074655 and parameters: {'embedding_dim': 73, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:40:29,019] Trial 43 finished with value: -143.8454161736745 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:40:33,839] Trial 44 finished with value: -39.27439317518788 and parameters: {'embedding_dim': 87, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:40:40,913] Trial 45 finished with value: -220.45718799518824 and parameters: {'embedding_dim': 77, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:40:46,131] Trial 46 finished with value: -55.17304861020244 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:40:52,572] Trial 47 finished with value: -33.46266729116897 and parameters: {'embedding_dim': 68, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:40:58,168] Trial 48 finished with value: -31.999285636647564 and parameters: {'embedding_dim': 84, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:41:04,560] Trial 49 finished with value: -265.55986359834793 and parameters: {'embedding_dim': 107, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 20 with value: -0.537647277081665.
+[I 2025-12-17 14:41:09,645] A new study created in memory with name: no-name-5bef535e-67c7-411f-a1bd-45bf596ce621
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_7000_2_incheon_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_7000_2_incheon_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan7000_2_incheon.csv: Class 0=6745 | Class 1=6868
+Saved ../../data/data_oversampled/ctgan7000/ctgan7000_2_incheon.csv: Class 0=6745 | Class 1=6868 | Class 2=14637
+Processing ../../data/data_for_modeling/seoul_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/seoul_train.csv: Optimizing CTGAN for class 1...
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_7000_2_seoul_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_7000_2_seoul_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan7000_2_seoul.csv: Class 0=6352 | Class 1=6766
+Saved ../../data/data_oversampled/ctgan7000/ctgan7000_2_seoul.csv: Class 0=6352 | Class 1=6766 | Class 2=15823
+Processing ../../data/data_for_modeling/busan_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/busan_train.csv: Optimizing CTGAN for class 1...
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_7000_2_busan_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_7000_2_busan_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan7000_2_busan.csv: Class 0=6372 | Class 1=6419
+Saved ../../data/data_oversampled/ctgan7000/ctgan7000_2_busan.csv: Class 0=6372 | Class 1=6419 | Class 2=16457
+Processing ../../data/data_for_modeling/daegu_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/daegu_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-17 14:41:17,177] Trial 0 finished with value: -6643.811093609529 and parameters: {'embedding_dim': 460, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 0 with value: -6643.811093609529.
+[I 2025-12-17 14:41:24,070] Trial 1 finished with value: -1942.3988790204517 and parameters: {'embedding_dim': 474, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 1 with value: -1942.3988790204517.
+[I 2025-12-17 14:41:31,018] Trial 2 finished with value: -1923.2095518666438 and parameters: {'embedding_dim': 281, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 2 with value: -1923.2095518666438.
+[I 2025-12-17 14:41:35,910] Trial 3 finished with value: -6267.085940699357 and parameters: {'embedding_dim': 261, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 2 with value: -1923.2095518666438.
+[I 2025-12-17 14:41:50,063] Trial 4 finished with value: -858.5608866712923 and parameters: {'embedding_dim': 375, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 4 with value: -858.5608866712923.
+[I 2025-12-17 14:41:57,203] Trial 5 finished with value: -607.5564163010644 and parameters: {'embedding_dim': 396, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 5 with value: -607.5564163010644.
+[I 2025-12-17 14:42:02,032] Trial 6 finished with value: -2299.3595498169466 and parameters: {'embedding_dim': 296, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 5 with value: -607.5564163010644.
+[I 2025-12-17 14:42:15,712] Trial 7 finished with value: -206.2861220485283 and parameters: {'embedding_dim': 163, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 7 with value: -206.2861220485283.
+[I 2025-12-17 14:42:34,260] Trial 8 finished with value: -920.7815661457473 and parameters: {'embedding_dim': 507, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 7 with value: -206.2861220485283.
+[I 2025-12-17 14:42:38,810] Trial 9 finished with value: -435.18035983880156 and parameters: {'embedding_dim': 151, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 7 with value: -206.2861220485283.
+[I 2025-12-17 14:42:55,167] Trial 10 finished with value: -250.83180579594782 and parameters: {'embedding_dim': 138, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 7 with value: -206.2861220485283.
+[I 2025-12-17 14:43:11,576] Trial 11 finished with value: -74.971086553062 and parameters: {'embedding_dim': 146, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 11 with value: -74.971086553062.
+[I 2025-12-17 14:43:25,249] Trial 12 finished with value: -444.3509467497749 and parameters: {'embedding_dim': 214, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 11 with value: -74.971086553062.
+[I 2025-12-17 14:43:38,776] Trial 13 finished with value: -367.48621366570256 and parameters: {'embedding_dim': 202, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 11 with value: -74.971086553062.
+[I 2025-12-17 14:44:01,232] Trial 14 finished with value: -385.5657141253515 and parameters: {'embedding_dim': 196, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 11 with value: -74.971086553062.
+[I 2025-12-17 14:44:12,149] Trial 15 finished with value: -238.39858278769333 and parameters: {'embedding_dim': 133, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 11 with value: -74.971086553062.
+[I 2025-12-17 14:44:26,042] Trial 16 finished with value: -366.56502351924047 and parameters: {'embedding_dim': 244, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 11 with value: -74.971086553062.
+[I 2025-12-17 14:44:48,474] Trial 17 finished with value: -300.63107794572477 and parameters: {'embedding_dim': 170, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 11 with value: -74.971086553062.
+[I 2025-12-17 14:44:59,283] Trial 18 finished with value: -710.3697058661833 and parameters: {'embedding_dim': 335, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 11 with value: -74.971086553062.
+[I 2025-12-17 14:45:17,803] Trial 19 finished with value: -170.27696616575716 and parameters: {'embedding_dim': 228, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 11 with value: -74.971086553062.
+[I 2025-12-17 14:45:33,390] Trial 20 finished with value: -360.3607412222356 and parameters: {'embedding_dim': 234, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 11 with value: -74.971086553062.
+[I 2025-12-17 14:45:52,500] Trial 21 finished with value: -161.2890763508171 and parameters: {'embedding_dim': 174, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 11 with value: -74.971086553062.
+[I 2025-12-17 14:46:08,879] Trial 22 finished with value: -201.34702396725564 and parameters: {'embedding_dim': 180, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 11 with value: -74.971086553062.
+[I 2025-12-17 14:46:25,721] Trial 23 finished with value: -376.07614280335713 and parameters: {'embedding_dim': 218, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 11 with value: -74.971086553062.
+[I 2025-12-17 14:46:40,917] Trial 24 finished with value: -269.0229881247558 and parameters: {'embedding_dim': 323, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 11 with value: -74.971086553062.
+[I 2025-12-17 14:46:57,353] Trial 25 finished with value: -183.03485016385022 and parameters: {'embedding_dim': 184, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 11 with value: -74.971086553062.
+[I 2025-12-17 14:47:10,936] Trial 26 finished with value: -402.3600664978427 and parameters: {'embedding_dim': 250, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 11 with value: -74.971086553062.
+[I 2025-12-17 14:47:24,636] Trial 27 finished with value: -616.0353040671113 and parameters: {'embedding_dim': 132, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 11 with value: -74.971086553062.
+[I 2025-12-17 14:47:48,676] Trial 28 finished with value: -143.5551241359208 and parameters: {'embedding_dim': 282, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 11 with value: -74.971086553062.
+[I 2025-12-17 14:48:09,474] Trial 29 finished with value: -367.1697832529961 and parameters: {'embedding_dim': 284, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 11 with value: -74.971086553062.
+[I 2025-12-17 14:48:26,317] A new study created in memory with name: no-name-8a5ea139-6006-4b19-b6c1-4d56b19c05e5
+[I 2025-12-17 14:48:32,252] Trial 0 finished with value: -55.26023001532667 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -55.26023001532667.
+[I 2025-12-17 14:48:35,711] Trial 1 finished with value: -45.81516160449396 and parameters: {'embedding_dim': 83, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 1 with value: -45.81516160449396.
+[I 2025-12-17 14:48:41,323] Trial 2 finished with value: -25.257571187540947 and parameters: {'embedding_dim': 87, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -25.257571187540947.
+[I 2025-12-17 14:48:46,230] Trial 3 finished with value: -83.37408025346687 and parameters: {'embedding_dim': 69, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -25.257571187540947.
+[I 2025-12-17 14:48:53,519] Trial 4 finished with value: -77.83554586380623 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -25.257571187540947.
+[I 2025-12-17 14:49:00,713] Trial 5 finished with value: -111.45111228036157 and parameters: {'embedding_dim': 91, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -25.257571187540947.
+[I 2025-12-17 14:49:05,936] Trial 6 finished with value: -247.25956087043664 and parameters: {'embedding_dim': 110, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -25.257571187540947.
+[I 2025-12-17 14:49:09,612] Trial 7 finished with value: -78.01896363811781 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -25.257571187540947.
+[I 2025-12-17 14:49:16,481] Trial 8 finished with value: -25.187600871854848 and parameters: {'embedding_dim': 107, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 8 with value: -25.187600871854848.
+[I 2025-12-17 14:49:22,073] Trial 9 finished with value: -322.6578342541041 and parameters: {'embedding_dim': 67, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 8 with value: -25.187600871854848.
+[I 2025-12-17 14:49:28,975] Trial 10 finished with value: -38.40177287621369 and parameters: {'embedding_dim': 126, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 8 with value: -25.187600871854848.
+[I 2025-12-17 14:49:35,816] Trial 11 finished with value: -322.75907145671584 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 8 with value: -25.187600871854848.
+[I 2025-12-17 14:49:43,136] Trial 12 finished with value: -104.47816558565881 and parameters: {'embedding_dim': 116, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 8 with value: -25.187600871854848.
+[I 2025-12-17 14:49:48,237] Trial 13 finished with value: -31.91670482948667 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 8 with value: -25.187600871854848.
+[I 2025-12-17 14:49:53,190] Trial 14 finished with value: -32.11117768119579 and parameters: {'embedding_dim': 119, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 8 with value: -25.187600871854848.
+[I 2025-12-17 14:50:00,478] Trial 15 finished with value: -25.48765938770018 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 8 with value: -25.187600871854848.
+[I 2025-12-17 14:50:05,602] Trial 16 finished with value: -36.64143557210289 and parameters: {'embedding_dim': 88, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 8 with value: -25.187600871854848.
+[I 2025-12-17 14:50:12,908] Trial 17 finished with value: -40.53398981653572 and parameters: {'embedding_dim': 107, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 8 with value: -25.187600871854848.
+[I 2025-12-17 14:50:18,043] Trial 18 finished with value: -97.11852425413718 and parameters: {'embedding_dim': 99, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 8 with value: -25.187600871854848.
+[I 2025-12-17 14:50:22,992] Trial 19 finished with value: -2.6908663531063066 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 19 with value: -2.6908663531063066.
+[I 2025-12-17 14:50:31,689] Trial 20 finished with value: -120.5214531064602 and parameters: {'embedding_dim': 72, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 19 with value: -2.6908663531063066.
+[I 2025-12-17 14:50:36,552] Trial 21 finished with value: -35.917508322506286 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 19 with value: -2.6908663531063066.
+[I 2025-12-17 14:50:41,504] Trial 22 finished with value: -47.531233098823584 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 19 with value: -2.6908663531063066.
+[I 2025-12-17 14:50:46,466] Trial 23 finished with value: -142.87879895932477 and parameters: {'embedding_dim': 94, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 19 with value: -2.6908663531063066.
+[I 2025-12-17 14:50:51,576] Trial 24 finished with value: -70.96859662774554 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 19 with value: -2.6908663531063066.
+[I 2025-12-17 14:50:54,890] Trial 25 finished with value: -198.96086332630563 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 19 with value: -2.6908663531063066.
+[I 2025-12-17 14:51:02,152] Trial 26 finished with value: -98.31159579358334 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 19 with value: -2.6908663531063066.
+[I 2025-12-17 14:51:07,100] Trial 27 finished with value: -120.80182468581768 and parameters: {'embedding_dim': 88, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 19 with value: -2.6908663531063066.
+[I 2025-12-17 14:51:14,413] Trial 28 finished with value: -62.94768382648125 and parameters: {'embedding_dim': 117, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 19 with value: -2.6908663531063066.
+[I 2025-12-17 14:51:17,815] Trial 29 finished with value: -778.4988283097321 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 19 with value: -2.6908663531063066.
+[I 2025-12-17 14:51:23,371] Trial 30 finished with value: -102.59284486623999 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 19 with value: -2.6908663531063066.
+[I 2025-12-17 14:51:32,867] Trial 31 finished with value: -47.95968515613455 and parameters: {'embedding_dim': 112, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 19 with value: -2.6908663531063066.
+[I 2025-12-17 14:51:40,181] Trial 32 finished with value: -21.19239232422766 and parameters: {'embedding_dim': 99, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 19 with value: -2.6908663531063066.
+[I 2025-12-17 14:51:47,490] Trial 33 finished with value: -20.905905995737832 and parameters: {'embedding_dim': 98, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 19 with value: -2.6908663531063066.
+[I 2025-12-17 14:51:54,796] Trial 34 finished with value: -125.73818022732847 and parameters: {'embedding_dim': 98, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 19 with value: -2.6908663531063066.
+[I 2025-12-17 14:52:02,085] Trial 35 finished with value: -1.1656918582395654 and parameters: {'embedding_dim': 106, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 35 with value: -1.1656918582395654.
+[I 2025-12-17 14:52:09,395] Trial 36 finished with value: -173.5839782742025 and parameters: {'embedding_dim': 103, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 35 with value: -1.1656918582395654.
+[I 2025-12-17 14:52:16,679] Trial 37 finished with value: -16.85995625055659 and parameters: {'embedding_dim': 94, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 35 with value: -1.1656918582395654.
+[I 2025-12-17 14:52:24,040] Trial 38 finished with value: -18.951745643866847 and parameters: {'embedding_dim': 123, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 35 with value: -1.1656918582395654.
+[I 2025-12-17 14:52:31,333] Trial 39 finished with value: -113.04485780805355 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 35 with value: -1.1656918582395654.
+[I 2025-12-17 14:52:40,552] Trial 40 finished with value: -10.316705810437021 and parameters: {'embedding_dim': 123, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 35 with value: -1.1656918582395654.
+[I 2025-12-17 14:52:47,887] Trial 41 finished with value: -67.11849218947151 and parameters: {'embedding_dim': 124, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 35 with value: -1.1656918582395654.
+[I 2025-12-17 14:52:55,263] Trial 42 finished with value: -27.854200783553633 and parameters: {'embedding_dim': 123, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 35 with value: -1.1656918582395654.
+[I 2025-12-17 14:53:02,534] Trial 43 finished with value: -58.02588521158401 and parameters: {'embedding_dim': 113, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 35 with value: -1.1656918582395654.
+[I 2025-12-17 14:53:09,834] Trial 44 finished with value: -10.824922542005154 and parameters: {'embedding_dim': 121, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 35 with value: -1.1656918582395654.
+[I 2025-12-17 14:53:17,680] Trial 45 finished with value: -234.89896782798036 and parameters: {'embedding_dim': 120, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 35 with value: -1.1656918582395654.
+[I 2025-12-17 14:53:24,229] Trial 46 finished with value: -47.9552348803429 and parameters: {'embedding_dim': 109, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 35 with value: -1.1656918582395654.
+[I 2025-12-17 14:53:31,628] Trial 47 finished with value: -16.735107038622345 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 35 with value: -1.1656918582395654.
+[I 2025-12-17 14:53:38,913] Trial 48 finished with value: -71.28572750724638 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 35 with value: -1.1656918582395654.
+[I 2025-12-17 14:53:44,343] Trial 49 finished with value: -114.86256382731526 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 35 with value: -1.1656918582395654.
+[I 2025-12-17 14:53:51,744] A new study created in memory with name: no-name-d96c9895-7e64-4842-a42d-460b74c4cad9
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_7000_2_daegu_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_7000_2_daegu_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan7000_2_daegu.csv: Class 0=6904 | Class 1=6500
+Saved ../../data/data_oversampled/ctgan7000/ctgan7000_2_daegu.csv: Class 0=6904 | Class 1=6500 | Class 2=16803
+Processing ../../data/data_for_modeling/daejeon_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/daejeon_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-17 14:54:16,064] Trial 0 finished with value: -568.7127550900086 and parameters: {'embedding_dim': 162, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 0 with value: -568.7127550900086.
+[I 2025-12-17 14:54:24,742] Trial 1 finished with value: -3480.086711469972 and parameters: {'embedding_dim': 339, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 0 with value: -568.7127550900086.
+[I 2025-12-17 14:55:11,216] Trial 2 finished with value: -543.8006302591862 and parameters: {'embedding_dim': 421, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -543.8006302591862.
+[I 2025-12-17 14:55:26,049] Trial 3 finished with value: -8495.287364581616 and parameters: {'embedding_dim': 397, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 2 with value: -543.8006302591862.
+[I 2025-12-17 14:56:07,749] Trial 4 finished with value: -321.8509092451828 and parameters: {'embedding_dim': 359, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 4 with value: -321.8509092451828.
+[I 2025-12-17 14:56:30,823] Trial 5 finished with value: -601.8079627144277 and parameters: {'embedding_dim': 151, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 4 with value: -321.8509092451828.
+[I 2025-12-17 14:57:17,601] Trial 6 finished with value: -601.3833385658722 and parameters: {'embedding_dim': 412, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -321.8509092451828.
+[I 2025-12-17 14:57:40,869] Trial 7 finished with value: -105.81036005415939 and parameters: {'embedding_dim': 467, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -105.81036005415939.
+[I 2025-12-17 14:58:26,478] Trial 8 finished with value: -862.7762899598871 and parameters: {'embedding_dim': 204, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 7 with value: -105.81036005415939.
+[I 2025-12-17 14:58:37,881] Trial 9 finished with value: -549.1908352795303 and parameters: {'embedding_dim': 371, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 7 with value: -105.81036005415939.
+[I 2025-12-17 14:59:38,301] Trial 10 finished with value: -578.3898491719544 and parameters: {'embedding_dim': 501, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 7 with value: -105.81036005415939.
+[I 2025-12-17 15:00:21,971] Trial 11 finished with value: -307.94416693867686 and parameters: {'embedding_dim': 263, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 7 with value: -105.81036005415939.
+[I 2025-12-17 15:00:59,848] Trial 12 finished with value: -813.0850415878268 and parameters: {'embedding_dim': 262, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 7 with value: -105.81036005415939.
+[I 2025-12-17 15:01:33,937] Trial 13 finished with value: -161.66253270691786 and parameters: {'embedding_dim': 276, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 7 with value: -105.81036005415939.
+[I 2025-12-17 15:02:08,114] Trial 14 finished with value: -1.999833889758735 and parameters: {'embedding_dim': 507, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -1.999833889758735.
+[I 2025-12-17 15:02:34,839] Trial 15 finished with value: -673.4536368761788 and parameters: {'embedding_dim': 512, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 14 with value: -1.999833889758735.
+[I 2025-12-17 15:03:08,935] Trial 16 finished with value: -4.109347892284179 and parameters: {'embedding_dim': 461, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -1.999833889758735.
+[I 2025-12-17 15:03:46,433] Trial 17 finished with value: -1070.2236407154583 and parameters: {'embedding_dim': 452, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -1.999833889758735.
+[I 2025-12-17 15:04:34,527] Trial 18 finished with value: -170.76742435391415 and parameters: {'embedding_dim': 460, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -1.999833889758735.
+[I 2025-12-17 15:05:08,610] Trial 19 finished with value: -20.39810782412804 and parameters: {'embedding_dim': 485, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -1.999833889758735.
+[I 2025-12-17 15:05:24,938] Trial 20 finished with value: -299.5099301889373 and parameters: {'embedding_dim': 439, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 14 with value: -1.999833889758735.
+[I 2025-12-17 15:06:02,586] Trial 21 finished with value: -269.832958610828 and parameters: {'embedding_dim': 487, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -1.999833889758735.
+[I 2025-12-17 15:06:38,252] Trial 22 finished with value: -186.96582939735737 and parameters: {'embedding_dim': 510, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -1.999833889758735.
+[I 2025-12-17 15:07:13,576] Trial 23 finished with value: -21.17464990974954 and parameters: {'embedding_dim': 478, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -1.999833889758735.
+[I 2025-12-17 15:07:37,142] Trial 24 finished with value: -73.14005491413658 and parameters: {'embedding_dim': 397, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 14 with value: -1.999833889758735.
+[I 2025-12-17 15:08:12,133] Trial 25 finished with value: -576.1548000754358 and parameters: {'embedding_dim': 432, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -1.999833889758735.
+[I 2025-12-17 15:09:01,775] Trial 26 finished with value: -2226.45003571342 and parameters: {'embedding_dim': 299, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -1.999833889758735.
+[I 2025-12-17 15:09:38,908] Trial 27 finished with value: -1853.2751843466547 and parameters: {'embedding_dim': 475, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -1.999833889758735.
+[I 2025-12-17 15:09:51,738] Trial 28 finished with value: -525.1912529347928 and parameters: {'embedding_dim': 376, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 14 with value: -1.999833889758735.
+[I 2025-12-17 15:10:39,884] Trial 29 finished with value: -767.6516926936382 and parameters: {'embedding_dim': 445, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -1.999833889758735.
+[I 2025-12-17 15:11:17,213] A new study created in memory with name: no-name-68a8d683-c789-4fa7-bcfd-c1d2d36571aa
+[I 2025-12-17 15:11:20,636] Trial 0 finished with value: -88.34374594910767 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -88.34374594910767.
+[I 2025-12-17 15:11:25,903] Trial 1 finished with value: -103.69668366420112 and parameters: {'embedding_dim': 124, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -88.34374594910767.
+[I 2025-12-17 15:11:29,308] Trial 2 finished with value: -11.501840573461147 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -11.501840573461147.
+[I 2025-12-17 15:11:32,626] Trial 3 finished with value: -267.57943444903225 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -11.501840573461147.
+[I 2025-12-17 15:11:37,609] Trial 4 finished with value: -74.94788684320176 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -11.501840573461147.
+[I 2025-12-17 15:11:40,839] Trial 5 finished with value: -30.046619566074078 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -11.501840573461147.
+[I 2025-12-17 15:11:44,231] Trial 6 finished with value: -313.58428790924467 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -11.501840573461147.
+[I 2025-12-17 15:11:47,532] Trial 7 finished with value: -243.6551025473574 and parameters: {'embedding_dim': 89, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -11.501840573461147.
+[I 2025-12-17 15:11:50,919] Trial 8 finished with value: -125.63405101557859 and parameters: {'embedding_dim': 87, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -11.501840573461147.
+[I 2025-12-17 15:11:54,157] Trial 9 finished with value: -116.95999631818813 and parameters: {'embedding_dim': 120, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -11.501840573461147.
+[I 2025-12-17 15:12:00,572] Trial 10 finished with value: -102.04890966912227 and parameters: {'embedding_dim': 66, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -11.501840573461147.
+[I 2025-12-17 15:12:05,355] Trial 11 finished with value: -150.83121199404238 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -11.501840573461147.
+[I 2025-12-17 15:12:12,519] Trial 12 finished with value: -58.94523851576544 and parameters: {'embedding_dim': 109, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -11.501840573461147.
+[I 2025-12-17 15:12:17,469] Trial 13 finished with value: -63.33338481852885 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -11.501840573461147.
+[I 2025-12-17 15:12:20,625] Trial 14 finished with value: -48.40062298731413 and parameters: {'embedding_dim': 115, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 2 with value: -11.501840573461147.
+[I 2025-12-17 15:12:25,868] Trial 15 finished with value: -8.156439625871473 and parameters: {'embedding_dim': 79, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -8.156439625871473.
+[I 2025-12-17 15:12:33,004] Trial 16 finished with value: -145.57316762314068 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -8.156439625871473.
+[I 2025-12-17 15:12:38,282] Trial 17 finished with value: -93.47519042357462 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -8.156439625871473.
+[I 2025-12-17 15:12:45,439] Trial 18 finished with value: -72.25231487274709 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -8.156439625871473.
+[I 2025-12-17 15:12:50,689] Trial 19 finished with value: -42.743248298799955 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -8.156439625871473.
+[I 2025-12-17 15:12:55,982] Trial 20 finished with value: -84.98172272138333 and parameters: {'embedding_dim': 81, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -8.156439625871473.
+[I 2025-12-17 15:12:59,236] Trial 21 finished with value: -89.33398718360431 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 15 with value: -8.156439625871473.
+[I 2025-12-17 15:13:02,473] Trial 22 finished with value: -40.1413657526568 and parameters: {'embedding_dim': 71, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 15 with value: -8.156439625871473.
+[I 2025-12-17 15:13:05,629] Trial 23 finished with value: -137.03101186886883 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 15 with value: -8.156439625871473.
+[I 2025-12-17 15:13:10,877] Trial 24 finished with value: -15.570941881148276 and parameters: {'embedding_dim': 112, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -8.156439625871473.
+[I 2025-12-17 15:13:16,146] Trial 25 finished with value: -18.905284407962938 and parameters: {'embedding_dim': 112, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -8.156439625871473.
+[I 2025-12-17 15:13:21,430] Trial 26 finished with value: -186.02702152355127 and parameters: {'embedding_dim': 116, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -8.156439625871473.
+[I 2025-12-17 15:13:28,596] Trial 27 finished with value: -69.9492389877989 and parameters: {'embedding_dim': 125, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -8.156439625871473.
+[I 2025-12-17 15:13:34,002] Trial 28 finished with value: -86.86045195789517 and parameters: {'embedding_dim': 100, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -8.156439625871473.
+[I 2025-12-17 15:13:39,254] Trial 29 finished with value: -68.42350805366499 and parameters: {'embedding_dim': 108, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -8.156439625871473.
+[I 2025-12-17 15:13:46,378] Trial 30 finished with value: -17.338959407454116 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -8.156439625871473.
+[I 2025-12-17 15:13:53,496] Trial 31 finished with value: -26.845858822580364 and parameters: {'embedding_dim': 94, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -8.156439625871473.
+[I 2025-12-17 15:14:00,592] Trial 32 finished with value: -28.845274897502126 and parameters: {'embedding_dim': 105, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -8.156439625871473.
+[I 2025-12-17 15:14:05,897] Trial 33 finished with value: -21.32005370630816 and parameters: {'embedding_dim': 120, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -8.156439625871473.
+[I 2025-12-17 15:14:13,039] Trial 34 finished with value: -43.76677496871775 and parameters: {'embedding_dim': 91, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -8.156439625871473.
+[I 2025-12-17 15:14:18,287] Trial 35 finished with value: -2.3251571916305456 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 35 with value: -2.3251571916305456.
+[I 2025-12-17 15:14:23,588] Trial 36 finished with value: -22.198661884775035 and parameters: {'embedding_dim': 76, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 35 with value: -2.3251571916305456.
+[I 2025-12-17 15:14:28,952] Trial 37 finished with value: -158.18609250527797 and parameters: {'embedding_dim': 83, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 35 with value: -2.3251571916305456.
+[I 2025-12-17 15:14:33,842] Trial 38 finished with value: -265.5647402524756 and parameters: {'embedding_dim': 77, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 35 with value: -2.3251571916305456.
+[I 2025-12-17 15:14:39,142] Trial 39 finished with value: -44.69348921627205 and parameters: {'embedding_dim': 71, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 35 with value: -2.3251571916305456.
+[I 2025-12-17 15:14:42,537] Trial 40 finished with value: -19.41869248979269 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 35 with value: -2.3251571916305456.
+[I 2025-12-17 15:14:47,801] Trial 41 finished with value: -64.06014216859705 and parameters: {'embedding_dim': 81, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 35 with value: -2.3251571916305456.
+[I 2025-12-17 15:14:53,044] Trial 42 finished with value: -65.33790735539822 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 35 with value: -2.3251571916305456.
+[I 2025-12-17 15:15:00,246] Trial 43 finished with value: -9.32108868048632 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 35 with value: -2.3251571916305456.
+[I 2025-12-17 15:15:05,593] Trial 44 finished with value: -37.85794344471672 and parameters: {'embedding_dim': 123, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 35 with value: -2.3251571916305456.
+[I 2025-12-17 15:15:10,940] Trial 45 finished with value: -0.8541462592401081 and parameters: {'embedding_dim': 112, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 45 with value: -0.8541462592401081.
+[I 2025-12-17 15:15:14,182] Trial 46 finished with value: -271.7780906864045 and parameters: {'embedding_dim': 120, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 45 with value: -0.8541462592401081.
+[I 2025-12-17 15:15:21,325] Trial 47 finished with value: -51.89669872370273 and parameters: {'embedding_dim': 116, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 45 with value: -0.8541462592401081.
+[I 2025-12-17 15:15:24,566] Trial 48 finished with value: -102.00197705656805 and parameters: {'embedding_dim': 102, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 45 with value: -0.8541462592401081.
+[I 2025-12-17 15:15:29,829] Trial 49 finished with value: -160.47101733518275 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 45 with value: -0.8541462592401081.
+[I 2025-12-17 15:15:35,204] A new study created in memory with name: no-name-6801cfb1-9e80-46b5-9179-8c64129733fe
+[I 2025-12-17 15:15:43,106] Trial 0 finished with value: -4819.273858766554 and parameters: {'embedding_dim': 193, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 0 with value: -4819.273858766554.
+[I 2025-12-17 15:16:24,375] Trial 1 finished with value: -763.0481454867564 and parameters: {'embedding_dim': 471, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 1 with value: -763.0481454867564.
+[I 2025-12-17 15:17:32,449] Trial 2 finished with value: -357.03511434581276 and parameters: {'embedding_dim': 271, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 2 with value: -357.03511434581276.
+[I 2025-12-17 15:18:14,453] Trial 3 finished with value: -1570.6707186294423 and parameters: {'embedding_dim': 209, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 2 with value: -357.03511434581276.
+[I 2025-12-17 15:18:34,869] Trial 4 finished with value: -973.0569515557154 and parameters: {'embedding_dim': 456, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 2 with value: -357.03511434581276.
+[I 2025-12-17 15:18:43,544] Trial 5 finished with value: -3019.927321849143 and parameters: {'embedding_dim': 156, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 2 with value: -357.03511434581276.
+[I 2025-12-17 15:19:11,489] Trial 6 finished with value: -434.31833147749563 and parameters: {'embedding_dim': 361, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 2 with value: -357.03511434581276.
+[I 2025-12-17 15:19:39,591] Trial 7 finished with value: -520.4178005554261 and parameters: {'embedding_dim': 506, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 2 with value: -357.03511434581276.
+[I 2025-12-17 15:20:01,272] Trial 8 finished with value: -2659.203760256683 and parameters: {'embedding_dim': 355, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 2 with value: -357.03511434581276.
+[I 2025-12-17 15:20:59,425] Trial 9 finished with value: -110.65633198951686 and parameters: {'embedding_dim': 296, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 9 with value: -110.65633198951686.
+[I 2025-12-17 15:21:56,909] Trial 10 finished with value: -885.7011315658092 and parameters: {'embedding_dim': 274, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 9 with value: -110.65633198951686.
+[I 2025-12-17 15:22:54,176] Trial 11 finished with value: -621.0262147472042 and parameters: {'embedding_dim': 290, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 9 with value: -110.65633198951686.
+[I 2025-12-17 15:23:54,596] Trial 12 finished with value: -343.8498204188784 and parameters: {'embedding_dim': 252, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 9 with value: -110.65633198951686.
+[I 2025-12-17 15:24:51,172] Trial 13 finished with value: -399.70688880350593 and parameters: {'embedding_dim': 390, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 9 with value: -110.65633198951686.
+[I 2025-12-17 15:25:52,083] Trial 14 finished with value: -97.06409302558119 and parameters: {'embedding_dim': 220, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 14 with value: -97.06409302558119.
+[I 2025-12-17 15:26:40,484] Trial 15 finished with value: -375.09079419717193 and parameters: {'embedding_dim': 128, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -97.06409302558119.
+[I 2025-12-17 15:27:15,031] Trial 16 finished with value: -35.47502814726607 and parameters: {'embedding_dim': 210, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 16 with value: -35.47502814726607.
+[I 2025-12-17 15:27:52,018] Trial 17 finished with value: -34.56043983913314 and parameters: {'embedding_dim': 220, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 17 with value: -34.56043983913314.
+[I 2025-12-17 15:28:27,900] Trial 18 finished with value: -29.666014119761435 and parameters: {'embedding_dim': 172, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -29.666014119761435.
+[I 2025-12-17 15:29:05,270] Trial 19 finished with value: -111.21009768415036 and parameters: {'embedding_dim': 172, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -29.666014119761435.
+[I 2025-12-17 15:29:19,050] Trial 20 finished with value: -345.4011301284093 and parameters: {'embedding_dim': 136, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 18 with value: -29.666014119761435.
+[I 2025-12-17 15:29:55,079] Trial 21 finished with value: -218.01740292105205 and parameters: {'embedding_dim': 237, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -29.666014119761435.
+[I 2025-12-17 15:30:17,865] Trial 22 finished with value: -21.564871262617547 and parameters: {'embedding_dim': 187, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 22 with value: -21.564871262617547.
+[I 2025-12-17 15:30:43,385] Trial 23 finished with value: -30.11761234733315 and parameters: {'embedding_dim': 184, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 22 with value: -21.564871262617547.
+[I 2025-12-17 15:31:05,826] Trial 24 finished with value: -578.2948604541735 and parameters: {'embedding_dim': 180, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 22 with value: -21.564871262617547.
+[I 2025-12-17 15:31:30,917] Trial 25 finished with value: -2528.9367985412796 and parameters: {'embedding_dim': 162, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 22 with value: -21.564871262617547.
+[I 2025-12-17 15:31:53,986] Trial 26 finished with value: -423.45535079085624 and parameters: {'embedding_dim': 322, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 22 with value: -21.564871262617547.
+[I 2025-12-17 15:32:15,972] Trial 27 finished with value: -89.73922855794906 and parameters: {'embedding_dim': 185, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 22 with value: -21.564871262617547.
+[I 2025-12-17 15:32:26,741] Trial 28 finished with value: -983.8700421874483 and parameters: {'embedding_dim': 246, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 22 with value: -21.564871262617547.
+[I 2025-12-17 15:32:49,368] Trial 29 finished with value: -118.44890597954938 and parameters: {'embedding_dim': 147, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 22 with value: -21.564871262617547.
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_7000_2_daejeon_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_7000_2_daejeon_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan7000_2_daejeon.csv: Class 0=6348 | Class 1=6712
+Saved ../../data/data_oversampled/ctgan7000/ctgan7000_2_daejeon.csv: Class 0=6348 | Class 1=6712 | Class 2=15717
+Processing ../../data/data_for_modeling/gwangju_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/gwangju_train.csv: Optimizing CTGAN for class 1...
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_7000_2_gwangju_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_7000_2_gwangju_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan7000_2_gwangju.csv: Class 0=5908 | Class 1=6554
+Saved ../../data/data_oversampled/ctgan7000/ctgan7000_2_gwangju.csv: Class 0=5908 | Class 1=6554 | Class 2=15760
+
+Running ctgan_sample_7000_3.py...
+[I 2025-12-17 15:33:15,759] A new study created in memory with name: no-name-8beeb359-037d-45fa-9395-c3f114e3b3e0
+[I 2025-12-17 15:33:41,736] Trial 0 finished with value: -27.265615906483113 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -27.265615906483113.
+[I 2025-12-17 15:34:07,138] Trial 1 finished with value: -12.381896093075754 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 1 with value: -12.381896093075754.
+[I 2025-12-17 15:34:27,534] Trial 2 finished with value: -19.014359552540533 and parameters: {'embedding_dim': 126, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -12.381896093075754.
+[I 2025-12-17 15:34:37,544] Trial 3 finished with value: -35.50069492116436 and parameters: {'embedding_dim': 104, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -12.381896093075754.
+[I 2025-12-17 15:34:45,143] Trial 4 finished with value: -39.257248128139516 and parameters: {'embedding_dim': 65, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -12.381896093075754.
+[I 2025-12-17 15:35:10,191] Trial 5 finished with value: -9.436429052159784 and parameters: {'embedding_dim': 99, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 5 with value: -9.436429052159784.
+[I 2025-12-17 15:35:14,069] Trial 6 finished with value: -336.985924996185 and parameters: {'embedding_dim': 70, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 5 with value: -9.436429052159784.
+[I 2025-12-17 15:35:17,959] Trial 7 finished with value: -70.11911772059807 and parameters: {'embedding_dim': 126, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 5 with value: -9.436429052159784.
+[I 2025-12-17 15:35:28,018] Trial 8 finished with value: -8.160233014711144 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 8 with value: -8.160233014711144.
+[I 2025-12-17 15:35:38,059] Trial 9 finished with value: -10.632302302291748 and parameters: {'embedding_dim': 123, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 8 with value: -8.160233014711144.
+[I 2025-12-17 15:35:44,732] Trial 10 finished with value: -58.43208995558714 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 8 with value: -8.160233014711144.
+[I 2025-12-17 15:35:56,810] Trial 11 finished with value: -75.30109702391616 and parameters: {'embedding_dim': 86, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 8 with value: -8.160233014711144.
+[I 2025-12-17 15:36:21,682] Trial 12 finished with value: -37.37658972664035 and parameters: {'embedding_dim': 81, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 8 with value: -8.160233014711144.
+[I 2025-12-17 15:36:31,728] Trial 13 finished with value: -17.730955512973793 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 8 with value: -8.160233014711144.
+[I 2025-12-17 15:36:56,609] Trial 14 finished with value: -44.02354102775708 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 8 with value: -8.160233014711144.
+[I 2025-12-17 15:37:15,089] Trial 15 finished with value: -247.39799474697986 and parameters: {'embedding_dim': 110, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 8 with value: -8.160233014711144.
+[I 2025-12-17 15:37:30,334] Trial 16 finished with value: -176.47454310972464 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 8 with value: -8.160233014711144.
+[I 2025-12-17 15:37:38,565] Trial 17 finished with value: -166.60564044122395 and parameters: {'embedding_dim': 85, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 8 with value: -8.160233014711144.
+[I 2025-12-17 15:37:57,384] Trial 18 finished with value: -29.9245579920982 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 8 with value: -8.160233014711144.
+[I 2025-12-17 15:38:03,148] Trial 19 finished with value: -216.47311564507473 and parameters: {'embedding_dim': 90, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 8 with value: -8.160233014711144.
+[I 2025-12-17 15:38:16,696] Trial 20 finished with value: -8.271176003807405 and parameters: {'embedding_dim': 108, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 8 with value: -8.160233014711144.
+[I 2025-12-17 15:38:30,203] Trial 21 finished with value: -72.00831689703526 and parameters: {'embedding_dim': 118, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 8 with value: -8.160233014711144.
+[I 2025-12-17 15:38:43,718] Trial 22 finished with value: -14.683210465275128 and parameters: {'embedding_dim': 103, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 8 with value: -8.160233014711144.
+[I 2025-12-17 15:39:00,431] Trial 23 finished with value: -3.834540219213892 and parameters: {'embedding_dim': 112, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 23 with value: -3.834540219213892.
+[I 2025-12-17 15:39:10,537] Trial 24 finished with value: -28.89796452359193 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 23 with value: -3.834540219213892.
+[I 2025-12-17 15:39:24,013] Trial 25 finished with value: -6.605304763333832 and parameters: {'embedding_dim': 118, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 23 with value: -3.834540219213892.
+[I 2025-12-17 15:39:37,475] Trial 26 finished with value: -5.859121494567483 and parameters: {'embedding_dim': 120, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 23 with value: -3.834540219213892.
+[I 2025-12-17 15:39:50,967] Trial 27 finished with value: -50.90898002704324 and parameters: {'embedding_dim': 117, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 23 with value: -3.834540219213892.
+[I 2025-12-17 15:40:04,462] Trial 28 finished with value: -69.17801902652013 and parameters: {'embedding_dim': 117, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 23 with value: -3.834540219213892.
+[I 2025-12-17 15:40:17,943] Trial 29 finished with value: -27.313647067634083 and parameters: {'embedding_dim': 121, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 23 with value: -3.834540219213892.
+[I 2025-12-17 15:40:34,168] Trial 30 finished with value: -13.638365415499171 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 23 with value: -3.834540219213892.
+[I 2025-12-17 15:40:44,221] Trial 31 finished with value: -19.04982634425547 and parameters: {'embedding_dim': 116, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 23 with value: -3.834540219213892.
+[I 2025-12-17 15:40:57,702] Trial 32 finished with value: -32.97440688531451 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 23 with value: -3.834540219213892.
+[I 2025-12-17 15:41:11,257] Trial 33 finished with value: -11.795963538112453 and parameters: {'embedding_dim': 122, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 23 with value: -3.834540219213892.
+[I 2025-12-17 15:41:24,566] Trial 34 finished with value: -6.932516625719194 and parameters: {'embedding_dim': 106, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 23 with value: -3.834540219213892.
+[I 2025-12-17 15:41:37,967] Trial 35 finished with value: -30.74934542318297 and parameters: {'embedding_dim': 107, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 23 with value: -3.834540219213892.
+[I 2025-12-17 15:41:45,669] Trial 36 finished with value: -12.525009220490375 and parameters: {'embedding_dim': 98, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 23 with value: -3.834540219213892.
+[I 2025-12-17 15:41:59,148] Trial 37 finished with value: -199.78604929639263 and parameters: {'embedding_dim': 113, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 23 with value: -3.834540219213892.
+[I 2025-12-17 15:42:06,805] Trial 38 finished with value: -11.925937140051506 and parameters: {'embedding_dim': 120, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 23 with value: -3.834540219213892.
+[I 2025-12-17 15:42:20,297] Trial 39 finished with value: -12.049760629256058 and parameters: {'embedding_dim': 106, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 23 with value: -3.834540219213892.
+[I 2025-12-17 15:42:35,711] Trial 40 finished with value: -38.14610126536892 and parameters: {'embedding_dim': 125, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 23 with value: -3.834540219213892.
+[I 2025-12-17 15:42:45,857] Trial 41 finished with value: -4.607601536287547 and parameters: {'embedding_dim': 65, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 23 with value: -3.834540219213892.
+[I 2025-12-17 15:42:55,809] Trial 42 finished with value: -79.44488366914098 and parameters: {'embedding_dim': 113, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 23 with value: -3.834540219213892.
+[I 2025-12-17 15:43:05,876] Trial 43 finished with value: -7.081415262300387 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 23 with value: -3.834540219213892.
+[I 2025-12-17 15:43:19,279] Trial 44 finished with value: -3.6951485571915104 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 44 with value: -3.6951485571915104.
+[I 2025-12-17 15:43:32,818] Trial 45 finished with value: -10.785128602175952 and parameters: {'embedding_dim': 95, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 44 with value: -3.6951485571915104.
+[I 2025-12-17 15:43:36,678] Trial 46 finished with value: -103.43790544269179 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 44 with value: -3.6951485571915104.
+[I 2025-12-17 15:44:01,730] Trial 47 finished with value: -129.93969008422795 and parameters: {'embedding_dim': 75, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 44 with value: -3.6951485571915104.
+[I 2025-12-17 15:44:11,775] Trial 48 finished with value: -118.97718941216148 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 44 with value: -3.6951485571915104.
+[I 2025-12-17 15:44:21,636] Trial 49 finished with value: -119.19152544656673 and parameters: {'embedding_dim': 124, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 44 with value: -3.6951485571915104.
+[I 2025-12-17 15:44:37,357] A new study created in memory with name: no-name-1c8b1a8e-3b69-495a-a014-7e7077a6fefa
+Using device: cuda
+Processing ../../data/data_for_modeling/incheon_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/incheon_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-17 15:45:14,871] Trial 0 finished with value: -137.36590537753597 and parameters: {'embedding_dim': 333, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 0 with value: -137.36590537753597.
+[I 2025-12-17 15:45:34,995] Trial 1 finished with value: -965.9792403769179 and parameters: {'embedding_dim': 349, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 0 with value: -137.36590537753597.
+[I 2025-12-17 15:46:05,469] Trial 2 finished with value: -72.60002858290314 and parameters: {'embedding_dim': 167, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 2 with value: -72.60002858290314.
+[I 2025-12-17 15:47:02,861] Trial 3 finished with value: -112.2621772099959 and parameters: {'embedding_dim': 433, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 2 with value: -72.60002858290314.
+[I 2025-12-17 15:47:28,229] Trial 4 finished with value: -385.00737516901046 and parameters: {'embedding_dim': 506, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 2 with value: -72.60002858290314.
+[I 2025-12-17 15:47:42,788] Trial 5 finished with value: -499.5131119591729 and parameters: {'embedding_dim': 503, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 2 with value: -72.60002858290314.
+[I 2025-12-17 15:48:41,128] Trial 6 finished with value: -540.968352787802 and parameters: {'embedding_dim': 157, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -72.60002858290314.
+[I 2025-12-17 15:49:20,410] Trial 7 finished with value: -204.1232983772694 and parameters: {'embedding_dim': 229, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -72.60002858290314.
+[I 2025-12-17 15:49:54,559] Trial 8 finished with value: -91.79277162026095 and parameters: {'embedding_dim': 489, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 2 with value: -72.60002858290314.
+[I 2025-12-17 15:51:04,288] Trial 9 finished with value: -34.59920007728677 and parameters: {'embedding_dim': 301, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 9 with value: -34.59920007728677.
+[I 2025-12-17 15:52:12,716] Trial 10 finished with value: -1000.2723024030928 and parameters: {'embedding_dim': 264, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 9 with value: -34.59920007728677.
+[I 2025-12-17 15:52:51,917] Trial 11 finished with value: -155.27627944625598 and parameters: {'embedding_dim': 143, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 9 with value: -34.59920007728677.
+[I 2025-12-17 15:53:49,814] Trial 12 finished with value: -278.7290885988669 and parameters: {'embedding_dim': 230, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 9 with value: -34.59920007728677.
+[I 2025-12-17 15:54:24,153] Trial 13 finished with value: -283.81470198452524 and parameters: {'embedding_dim': 372, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 9 with value: -34.59920007728677.
+[I 2025-12-17 15:56:18,231] Trial 14 finished with value: -1365.6893559310438 and parameters: {'embedding_dim': 289, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 9 with value: -34.59920007728677.
+[I 2025-12-17 15:57:14,545] Trial 15 finished with value: -147.48995124287143 and parameters: {'embedding_dim': 190, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 9 with value: -34.59920007728677.
+[I 2025-12-17 15:57:42,073] Trial 16 finished with value: -443.6551784309497 and parameters: {'embedding_dim': 406, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 9 with value: -34.59920007728677.
+[I 2025-12-17 15:58:21,073] Trial 17 finished with value: -389.1349865965383 and parameters: {'embedding_dim': 298, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 9 with value: -34.59920007728677.
+[I 2025-12-17 15:59:06,969] Trial 18 finished with value: -505.29039608433135 and parameters: {'embedding_dim': 189, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 9 with value: -34.59920007728677.
+[I 2025-12-17 16:00:42,192] Trial 19 finished with value: -682.6099536899227 and parameters: {'embedding_dim': 248, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 9 with value: -34.59920007728677.
+[I 2025-12-17 16:01:19,227] Trial 20 finished with value: -87.77883470551147 and parameters: {'embedding_dim': 192, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 9 with value: -34.59920007728677.
+[I 2025-12-17 16:01:56,995] Trial 21 finished with value: -295.1697129906832 and parameters: {'embedding_dim': 180, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 9 with value: -34.59920007728677.
+[I 2025-12-17 16:02:37,503] Trial 22 finished with value: -366.1873166498417 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 9 with value: -34.59920007728677.
+[I 2025-12-17 16:03:08,932] Trial 23 finished with value: -260.98812117676806 and parameters: {'embedding_dim': 212, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 9 with value: -34.59920007728677.
+[I 2025-12-17 16:03:47,247] Trial 24 finished with value: -76.37159485066974 and parameters: {'embedding_dim': 269, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 9 with value: -34.59920007728677.
+[I 2025-12-17 16:04:46,990] Trial 25 finished with value: -57.06736631022631 and parameters: {'embedding_dim': 292, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 9 with value: -34.59920007728677.
+[I 2025-12-17 16:05:33,374] Trial 26 finished with value: -767.2371396549313 and parameters: {'embedding_dim': 310, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 9 with value: -34.59920007728677.
+[I 2025-12-17 16:06:32,868] Trial 27 finished with value: -51.16216162852875 and parameters: {'embedding_dim': 355, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 9 with value: -34.59920007728677.
+[I 2025-12-17 16:07:29,223] Trial 28 finished with value: -327.42251970908575 and parameters: {'embedding_dim': 389, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 9 with value: -34.59920007728677.
+[I 2025-12-17 16:08:15,897] Trial 29 finished with value: -1234.6629025694817 and parameters: {'embedding_dim': 346, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 9 with value: -34.59920007728677.
+[I 2025-12-17 16:09:23,899] A new study created in memory with name: no-name-dbb1a2cc-8e2e-4ff9-ad61-8ec68ad3644f
+[I 2025-12-17 16:09:26,962] Trial 0 finished with value: -413.6456513462744 and parameters: {'embedding_dim': 123, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -413.6456513462744.
+[I 2025-12-17 16:09:32,138] Trial 1 finished with value: -260.6251761457483 and parameters: {'embedding_dim': 121, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -260.6251761457483.
+[I 2025-12-17 16:09:37,305] Trial 2 finished with value: -371.1588288577295 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -260.6251761457483.
+[I 2025-12-17 16:09:40,330] Trial 3 finished with value: -283.5431355592728 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 1 with value: -260.6251761457483.
+[I 2025-12-17 16:09:43,407] Trial 4 finished with value: -766.8154048327365 and parameters: {'embedding_dim': 101, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 1 with value: -260.6251761457483.
+[I 2025-12-17 16:09:46,552] Trial 5 finished with value: -92.65934708960975 and parameters: {'embedding_dim': 112, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 5 with value: -92.65934708960975.
+[I 2025-12-17 16:09:51,724] Trial 6 finished with value: -78.25594703079607 and parameters: {'embedding_dim': 91, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 6 with value: -78.25594703079607.
+[I 2025-12-17 16:09:56,451] Trial 7 finished with value: -498.96646284268235 and parameters: {'embedding_dim': 121, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 6 with value: -78.25594703079607.
+[I 2025-12-17 16:09:59,646] Trial 8 finished with value: -946.2204314266194 and parameters: {'embedding_dim': 89, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 6 with value: -78.25594703079607.
+[I 2025-12-17 16:10:04,347] Trial 9 finished with value: -185.56050970515884 and parameters: {'embedding_dim': 127, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 6 with value: -78.25594703079607.
+[I 2025-12-17 16:10:11,360] Trial 10 finished with value: -225.64543001898082 and parameters: {'embedding_dim': 69, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 6 with value: -78.25594703079607.
+[I 2025-12-17 16:10:18,002] Trial 11 finished with value: -474.55298134196653 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 6 with value: -78.25594703079607.
+[I 2025-12-17 16:10:25,051] Trial 12 finished with value: -178.96468536948402 and parameters: {'embedding_dim': 110, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 6 with value: -78.25594703079607.
+[I 2025-12-17 16:10:28,371] Trial 13 finished with value: -461.7431364586294 and parameters: {'embedding_dim': 108, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 6 with value: -78.25594703079607.
+[I 2025-12-17 16:10:33,291] Trial 14 finished with value: -276.99195305376065 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 6 with value: -78.25594703079607.
+[I 2025-12-17 16:10:36,344] Trial 15 finished with value: -814.0683512626282 and parameters: {'embedding_dim': 111, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 6 with value: -78.25594703079607.
+[I 2025-12-17 16:10:43,632] Trial 16 finished with value: -168.658232384949 and parameters: {'embedding_dim': 83, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 6 with value: -78.25594703079607.
+[I 2025-12-17 16:10:48,318] Trial 17 finished with value: -531.0074259313922 and parameters: {'embedding_dim': 67, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 6 with value: -78.25594703079607.
+[I 2025-12-17 16:10:53,603] Trial 18 finished with value: -56.93243193163911 and parameters: {'embedding_dim': 103, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -56.93243193163911.
+[I 2025-12-17 16:10:58,733] Trial 19 finished with value: -114.49542878473929 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -56.93243193163911.
+[I 2025-12-17 16:11:03,885] Trial 20 finished with value: -189.3746939920648 and parameters: {'embedding_dim': 104, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -56.93243193163911.
+[I 2025-12-17 16:11:09,060] Trial 21 finished with value: -414.10475367243765 and parameters: {'embedding_dim': 115, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -56.93243193163911.
+[I 2025-12-17 16:11:12,374] Trial 22 finished with value: -260.8308472395542 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 18 with value: -56.93243193163911.
+[I 2025-12-17 16:11:18,963] Trial 23 finished with value: -514.3328286154346 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 18 with value: -56.93243193163911.
+[I 2025-12-17 16:11:24,160] Trial 24 finished with value: -607.2733019409923 and parameters: {'embedding_dim': 106, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -56.93243193163911.
+[I 2025-12-17 16:11:27,222] Trial 25 finished with value: -352.8442362658214 and parameters: {'embedding_dim': 99, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 18 with value: -56.93243193163911.
+[I 2025-12-17 16:11:32,358] Trial 26 finished with value: -324.78099762572333 and parameters: {'embedding_dim': 90, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -56.93243193163911.
+[I 2025-12-17 16:11:39,457] Trial 27 finished with value: -346.84095321766824 and parameters: {'embedding_dim': 116, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 18 with value: -56.93243193163911.
+[I 2025-12-17 16:11:42,643] Trial 28 finished with value: -245.2784848714242 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 18 with value: -56.93243193163911.
+[I 2025-12-17 16:11:45,702] Trial 29 finished with value: -663.2049678667804 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 18 with value: -56.93243193163911.
+[I 2025-12-17 16:11:50,455] Trial 30 finished with value: -226.85437524109193 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 18 with value: -56.93243193163911.
+[I 2025-12-17 16:11:55,622] Trial 31 finished with value: -157.0210422312201 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -56.93243193163911.
+[I 2025-12-17 16:12:00,773] Trial 32 finished with value: -45.598297620281514 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -45.598297620281514.
+[I 2025-12-17 16:12:05,907] Trial 33 finished with value: -101.75980437754356 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -45.598297620281514.
+[I 2025-12-17 16:12:11,056] Trial 34 finished with value: -276.6935797612167 and parameters: {'embedding_dim': 118, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -45.598297620281514.
+[I 2025-12-17 16:12:16,219] Trial 35 finished with value: -444.94172702482354 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -45.598297620281514.
+[I 2025-12-17 16:12:19,522] Trial 36 finished with value: -758.0193306742864 and parameters: {'embedding_dim': 88, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 32 with value: -45.598297620281514.
+[I 2025-12-17 16:12:24,216] Trial 37 finished with value: -117.04287602089455 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 32 with value: -45.598297620281514.
+[I 2025-12-17 16:12:29,369] Trial 38 finished with value: -73.62143111853767 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -45.598297620281514.
+[I 2025-12-17 16:12:34,603] Trial 39 finished with value: -441.6972024946784 and parameters: {'embedding_dim': 124, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -45.598297620281514.
+[I 2025-12-17 16:12:39,811] Trial 40 finished with value: -68.2457902972368 and parameters: {'embedding_dim': 101, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -45.598297620281514.
+[I 2025-12-17 16:12:44,986] Trial 41 finished with value: -302.8336874149085 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -45.598297620281514.
+[I 2025-12-17 16:12:50,215] Trial 42 finished with value: -89.33754588112204 and parameters: {'embedding_dim': 106, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -45.598297620281514.
+[I 2025-12-17 16:12:55,365] Trial 43 finished with value: -123.2615142229982 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -45.598297620281514.
+[I 2025-12-17 16:13:00,520] Trial 44 finished with value: -181.33324736822033 and parameters: {'embedding_dim': 108, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -45.598297620281514.
+[I 2025-12-17 16:13:05,663] Trial 45 finished with value: -98.92619876861 and parameters: {'embedding_dim': 91, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -45.598297620281514.
+[I 2025-12-17 16:13:10,825] Trial 46 finished with value: -332.78590578126403 and parameters: {'embedding_dim': 102, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -45.598297620281514.
+[I 2025-12-17 16:13:15,967] Trial 47 finished with value: -150.63911171244305 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -45.598297620281514.
+[I 2025-12-17 16:13:20,917] Trial 48 finished with value: -552.0584389795051 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 32 with value: -45.598297620281514.
+[I 2025-12-17 16:13:28,538] Trial 49 finished with value: -164.56165598990646 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 32 with value: -45.598297620281514.
+[I 2025-12-17 16:13:33,781] A new study created in memory with name: no-name-a9fe7b1c-9aaf-423b-af14-ca34327b62d2
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_7000_3_incheon_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_7000_3_incheon_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan7000_3_incheon.csv: Class 0=6740 | Class 1=6821
+Saved ../../data/data_oversampled/ctgan7000/ctgan7000_3_incheon.csv: Class 0=6740 | Class 1=6821 | Class 2=14595
+Processing ../../data/data_for_modeling/seoul_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/seoul_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-17 16:14:09,884] Trial 0 finished with value: -534.6758669450095 and parameters: {'embedding_dim': 328, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 0 with value: -534.6758669450095.
+[I 2025-12-17 16:14:38,551] Trial 1 finished with value: -609.7705089725682 and parameters: {'embedding_dim': 245, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 0 with value: -534.6758669450095.
+[I 2025-12-17 16:15:12,438] Trial 2 finished with value: -508.62767448354487 and parameters: {'embedding_dim': 491, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -508.62767448354487.
+[I 2025-12-17 16:15:46,694] Trial 3 finished with value: -387.85026481283734 and parameters: {'embedding_dim': 373, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 3 with value: -387.85026481283734.
+[I 2025-12-17 16:16:01,588] Trial 4 finished with value: -306.74306782135614 and parameters: {'embedding_dim': 155, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 4 with value: -306.74306782135614.
+[I 2025-12-17 16:16:46,487] Trial 5 finished with value: -1242.8534443554424 and parameters: {'embedding_dim': 282, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -306.74306782135614.
+[I 2025-12-17 16:17:02,907] Trial 6 finished with value: -338.7479475485176 and parameters: {'embedding_dim': 252, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 4 with value: -306.74306782135614.
+[I 2025-12-17 16:17:25,813] Trial 7 finished with value: -4885.7389287454835 and parameters: {'embedding_dim': 387, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 4 with value: -306.74306782135614.
+[I 2025-12-17 16:17:37,299] Trial 8 finished with value: -406.0720524989741 and parameters: {'embedding_dim': 196, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 4 with value: -306.74306782135614.
+[I 2025-12-17 16:18:22,638] Trial 9 finished with value: -242.8032697129932 and parameters: {'embedding_dim': 168, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 9 with value: -242.8032697129932.
+[I 2025-12-17 16:19:31,139] Trial 10 finished with value: -1200.6282867717657 and parameters: {'embedding_dim': 145, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 9 with value: -242.8032697129932.
+[I 2025-12-17 16:19:45,791] Trial 11 finished with value: -245.82414319546103 and parameters: {'embedding_dim': 131, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 9 with value: -242.8032697129932.
+[I 2025-12-17 16:20:00,583] Trial 12 finished with value: -795.9286339567168 and parameters: {'embedding_dim': 138, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 9 with value: -242.8032697129932.
+[I 2025-12-17 16:20:43,114] Trial 13 finished with value: -325.10301123175003 and parameters: {'embedding_dim': 197, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 9 with value: -242.8032697129932.
+[I 2025-12-17 16:21:00,730] Trial 14 finished with value: -301.4642612005372 and parameters: {'embedding_dim': 203, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 9 with value: -242.8032697129932.
+[I 2025-12-17 16:21:35,023] Trial 15 finished with value: -912.0181987413326 and parameters: {'embedding_dim': 183, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 9 with value: -242.8032697129932.
+[I 2025-12-17 16:22:03,010] Trial 16 finished with value: -81.66315775281124 and parameters: {'embedding_dim': 507, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 16 with value: -81.66315775281124.
+[I 2025-12-17 16:22:30,229] Trial 17 finished with value: -86.82009895100175 and parameters: {'embedding_dim': 466, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 16 with value: -81.66315775281124.
+[I 2025-12-17 16:22:58,587] Trial 18 finished with value: -1021.8463778164328 and parameters: {'embedding_dim': 507, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 16 with value: -81.66315775281124.
+[I 2025-12-17 16:23:33,578] Trial 19 finished with value: -54.55108968552272 and parameters: {'embedding_dim': 457, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 19 with value: -54.55108968552272.
+[I 2025-12-17 16:24:08,386] Trial 20 finished with value: -178.4290100149456 and parameters: {'embedding_dim': 433, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 19 with value: -54.55108968552272.
+[I 2025-12-17 16:24:36,764] Trial 21 finished with value: -268.4072115188902 and parameters: {'embedding_dim': 456, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 19 with value: -54.55108968552272.
+[I 2025-12-17 16:25:11,701] Trial 22 finished with value: -405.60669239156215 and parameters: {'embedding_dim': 457, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 19 with value: -54.55108968552272.
+[I 2025-12-17 16:25:53,819] Trial 23 finished with value: -291.44418921730767 and parameters: {'embedding_dim': 416, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 19 with value: -54.55108968552272.
+[I 2025-12-17 16:26:30,944] Trial 24 finished with value: -313.9829203060643 and parameters: {'embedding_dim': 477, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 19 with value: -54.55108968552272.
+[I 2025-12-17 16:26:59,050] Trial 25 finished with value: -343.0709645555164 and parameters: {'embedding_dim': 390, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 19 with value: -54.55108968552272.
+[I 2025-12-17 16:27:13,134] Trial 26 finished with value: -659.5595389859991 and parameters: {'embedding_dim': 353, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 19 with value: -54.55108968552272.
+[I 2025-12-17 16:27:34,286] Trial 27 finished with value: -40.36377547449093 and parameters: {'embedding_dim': 512, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 27 with value: -40.36377547449093.
+[I 2025-12-17 16:27:55,593] Trial 28 finished with value: -83.60905337932354 and parameters: {'embedding_dim': 510, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 27 with value: -40.36377547449093.
+[I 2025-12-17 16:28:17,071] Trial 29 finished with value: -1424.304478909864 and parameters: {'embedding_dim': 419, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 27 with value: -40.36377547449093.
+[I 2025-12-17 16:28:39,068] A new study created in memory with name: no-name-89521490-2052-4b7c-bdea-28248920401a
+[I 2025-12-17 16:28:43,935] Trial 0 finished with value: -251.51165169043117 and parameters: {'embedding_dim': 95, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -251.51165169043117.
+[I 2025-12-17 16:28:50,731] Trial 1 finished with value: -30.41417837246038 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 1 with value: -30.41417837246038.
+[I 2025-12-17 16:28:57,522] Trial 2 finished with value: -24.373070052060157 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -24.373070052060157.
+[I 2025-12-17 16:29:00,995] Trial 3 finished with value: -421.4872354347029 and parameters: {'embedding_dim': 74, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -24.373070052060157.
+[I 2025-12-17 16:29:08,174] Trial 4 finished with value: -0.15912415497417692 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:29:13,201] Trial 5 finished with value: -1.1817515217106465 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:29:16,620] Trial 6 finished with value: -105.25862740561159 and parameters: {'embedding_dim': 112, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:29:23,384] Trial 7 finished with value: -19.4331152395454 and parameters: {'embedding_dim': 70, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:29:26,611] Trial 8 finished with value: -158.71610811331783 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:29:33,800] Trial 9 finished with value: -61.3876511652369 and parameters: {'embedding_dim': 112, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:29:39,166] Trial 10 finished with value: -130.44076025778688 and parameters: {'embedding_dim': 84, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:29:44,450] Trial 11 finished with value: -45.85655505218172 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:29:49,723] Trial 12 finished with value: -18.251334759242294 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:29:54,759] Trial 13 finished with value: -56.118163950421334 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:30:01,290] Trial 14 finished with value: -179.15753531644552 and parameters: {'embedding_dim': 123, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:30:06,435] Trial 15 finished with value: -13.072731802818488 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:30:13,684] Trial 16 finished with value: -122.65195463449193 and parameters: {'embedding_dim': 87, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:30:16,994] Trial 17 finished with value: -19.822775848087165 and parameters: {'embedding_dim': 65, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:30:22,329] Trial 18 finished with value: -22.301039019601244 and parameters: {'embedding_dim': 90, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:30:28,845] Trial 19 finished with value: -57.04245605098347 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:30:34,192] Trial 20 finished with value: -55.46084758276897 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:30:39,212] Trial 21 finished with value: -58.92788029533952 and parameters: {'embedding_dim': 80, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:30:44,246] Trial 22 finished with value: -85.06641433464108 and parameters: {'embedding_dim': 70, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:30:49,260] Trial 23 finished with value: -2.8443925158284404 and parameters: {'embedding_dim': 91, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:30:52,575] Trial 24 finished with value: -63.3739588144257 and parameters: {'embedding_dim': 91, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:30:57,599] Trial 25 finished with value: -21.79532119366041 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:31:04,361] Trial 26 finished with value: -77.65899405023517 and parameters: {'embedding_dim': 90, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:31:09,392] Trial 27 finished with value: -55.273981135053916 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:31:14,324] Trial 28 finished with value: -158.38705936538707 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:31:17,801] Trial 29 finished with value: -166.71182353001026 and parameters: {'embedding_dim': 95, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:31:24,271] Trial 30 finished with value: -103.25902510917794 and parameters: {'embedding_dim': 100, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:31:29,301] Trial 31 finished with value: -13.693907904856502 and parameters: {'embedding_dim': 80, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:31:34,322] Trial 32 finished with value: -23.198364327958092 and parameters: {'embedding_dim': 69, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:31:39,343] Trial 33 finished with value: -4.823341000976239 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:31:44,392] Trial 34 finished with value: -62.903302147675724 and parameters: {'embedding_dim': 94, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:31:49,417] Trial 35 finished with value: -63.376979176015126 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:31:56,122] Trial 36 finished with value: -31.21479054741351 and parameters: {'embedding_dim': 87, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:31:59,477] Trial 37 finished with value: -183.23057239483694 and parameters: {'embedding_dim': 127, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:32:04,824] Trial 38 finished with value: -42.82246294169659 and parameters: {'embedding_dim': 99, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:32:11,515] Trial 39 finished with value: -16.302334798988195 and parameters: {'embedding_dim': 68, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:32:15,064] Trial 40 finished with value: -52.64020037708976 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:32:20,079] Trial 41 finished with value: -24.76709141829963 and parameters: {'embedding_dim': 80, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:32:25,104] Trial 42 finished with value: -61.5349621929585 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:32:30,118] Trial 43 finished with value: -2.1929209127703473 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:32:35,145] Trial 44 finished with value: -59.458936762784646 and parameters: {'embedding_dim': 83, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:32:40,169] Trial 45 finished with value: -43.00878600395817 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:32:45,141] Trial 46 finished with value: -108.18908596115114 and parameters: {'embedding_dim': 87, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:32:50,210] Trial 47 finished with value: -16.772875147212417 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:32:55,618] Trial 48 finished with value: -31.724529368490714 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:33:00,698] Trial 49 finished with value: -94.3048677323145 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -0.15912415497417692.
+[I 2025-12-17 16:33:08,104] A new study created in memory with name: no-name-dd4d9325-9aaa-494d-9ffb-ab506fd2fbab
+[I 2025-12-17 16:33:26,529] Trial 0 finished with value: -778.0925614901305 and parameters: {'embedding_dim': 455, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 0 with value: -778.0925614901305.
+[I 2025-12-17 16:33:54,030] Trial 1 finished with value: -585.156291925492 and parameters: {'embedding_dim': 339, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 1 with value: -585.156291925492.
+[I 2025-12-17 16:34:17,329] Trial 2 finished with value: -468.60420118750005 and parameters: {'embedding_dim': 202, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 2 with value: -468.60420118750005.
+[I 2025-12-17 16:34:24,886] Trial 3 finished with value: -626.0713198996459 and parameters: {'embedding_dim': 366, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 2 with value: -468.60420118750005.
+[I 2025-12-17 16:34:43,368] Trial 4 finished with value: -1195.8017239790927 and parameters: {'embedding_dim': 315, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 2 with value: -468.60420118750005.
+[I 2025-12-17 16:34:53,200] Trial 5 finished with value: -870.7798249096506 and parameters: {'embedding_dim': 204, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 2 with value: -468.60420118750005.
+[I 2025-12-17 16:35:08,519] Trial 6 finished with value: -849.9524168676373 and parameters: {'embedding_dim': 432, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -468.60420118750005.
+[I 2025-12-17 16:35:28,709] Trial 7 finished with value: -1726.7044063775825 and parameters: {'embedding_dim': 277, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 2 with value: -468.60420118750005.
+[I 2025-12-17 16:35:39,359] Trial 8 finished with value: -2003.179028997435 and parameters: {'embedding_dim': 503, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 2 with value: -468.60420118750005.
+[I 2025-12-17 16:35:52,548] Trial 9 finished with value: -1358.3557676687597 and parameters: {'embedding_dim': 511, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 2 with value: -468.60420118750005.
+[I 2025-12-17 16:36:31,931] Trial 10 finished with value: -293.208114204633 and parameters: {'embedding_dim': 145, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 10 with value: -293.208114204633.
+[I 2025-12-17 16:37:12,688] Trial 11 finished with value: -313.48904685471683 and parameters: {'embedding_dim': 128, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 10 with value: -293.208114204633.
+[I 2025-12-17 16:37:54,698] Trial 12 finished with value: -1872.2433752489421 and parameters: {'embedding_dim': 133, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 10 with value: -293.208114204633.
+[I 2025-12-17 16:38:37,848] Trial 13 finished with value: -112.86269278391758 and parameters: {'embedding_dim': 130, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 13 with value: -112.86269278391758.
+[I 2025-12-17 16:39:16,451] Trial 14 finished with value: -519.4039946380163 and parameters: {'embedding_dim': 204, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 13 with value: -112.86269278391758.
+[I 2025-12-17 16:40:04,420] Trial 15 finished with value: -360.10759482619306 and parameters: {'embedding_dim': 251, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 13 with value: -112.86269278391758.
+[I 2025-12-17 16:40:44,356] Trial 16 finished with value: -912.0942900837762 and parameters: {'embedding_dim': 171, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 13 with value: -112.86269278391758.
+[I 2025-12-17 16:41:07,468] Trial 17 finished with value: -890.5785383452883 and parameters: {'embedding_dim': 259, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 13 with value: -112.86269278391758.
+[I 2025-12-17 16:41:40,560] Trial 18 finished with value: -603.3326137431221 and parameters: {'embedding_dim': 170, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 13 with value: -112.86269278391758.
+[I 2025-12-17 16:42:26,622] Trial 19 finished with value: -383.7262178822844 and parameters: {'embedding_dim': 166, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 13 with value: -112.86269278391758.
+[I 2025-12-17 16:43:09,981] Trial 20 finished with value: -187.06950975007436 and parameters: {'embedding_dim': 230, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 13 with value: -112.86269278391758.
+[I 2025-12-17 16:43:49,663] Trial 21 finished with value: -445.26422060445634 and parameters: {'embedding_dim': 208, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 13 with value: -112.86269278391758.
+[I 2025-12-17 16:44:32,045] Trial 22 finished with value: -426.12273015366225 and parameters: {'embedding_dim': 235, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 13 with value: -112.86269278391758.
+[I 2025-12-17 16:45:19,198] Trial 23 finished with value: -2307.5685332954513 and parameters: {'embedding_dim': 153, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 13 with value: -112.86269278391758.
+[I 2025-12-17 16:46:00,870] Trial 24 finished with value: -2249.435184375623 and parameters: {'embedding_dim': 302, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 13 with value: -112.86269278391758.
+[I 2025-12-17 16:46:34,694] Trial 25 finished with value: -891.3132915029064 and parameters: {'embedding_dim': 129, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 13 with value: -112.86269278391758.
+[I 2025-12-17 16:47:18,648] Trial 26 finished with value: -1227.404943673228 and parameters: {'embedding_dim': 221, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 13 with value: -112.86269278391758.
+[I 2025-12-17 16:48:07,429] Trial 27 finished with value: -441.989371679034 and parameters: {'embedding_dim': 164, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 13 with value: -112.86269278391758.
+[I 2025-12-17 16:48:26,705] Trial 28 finished with value: -384.61057719578525 and parameters: {'embedding_dim': 180, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 13 with value: -112.86269278391758.
+[I 2025-12-17 16:49:17,526] Trial 29 finished with value: -1453.5225109531325 and parameters: {'embedding_dim': 403, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 13 with value: -112.86269278391758.
+[I 2025-12-17 16:49:58,022] A new study created in memory with name: no-name-66a63ae7-adcf-44fa-a7c8-970c2746b93b
+[I 2025-12-17 16:50:04,424] Trial 0 finished with value: -498.0051854557756 and parameters: {'embedding_dim': 73, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -498.0051854557756.
+[I 2025-12-17 16:50:09,443] Trial 1 finished with value: -16.701277526911323 and parameters: {'embedding_dim': 87, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:50:14,442] Trial 2 finished with value: -35.253212295928044 and parameters: {'embedding_dim': 87, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:50:19,370] Trial 3 finished with value: -130.7317081133906 and parameters: {'embedding_dim': 119, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:50:24,139] Trial 4 finished with value: -226.2321043928891 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:50:29,364] Trial 5 finished with value: -181.6790268365446 and parameters: {'embedding_dim': 87, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:50:35,984] Trial 6 finished with value: -160.3304591708759 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:50:43,780] Trial 7 finished with value: -163.08791881009168 and parameters: {'embedding_dim': 112, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:50:49,806] Trial 8 finished with value: -123.90596085838364 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:50:54,780] Trial 9 finished with value: -573.2735014434555 and parameters: {'embedding_dim': 118, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:50:58,031] Trial 10 finished with value: -117.54956535601342 and parameters: {'embedding_dim': 67, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:51:01,264] Trial 11 finished with value: -326.99353932085904 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:51:04,544] Trial 12 finished with value: -384.31610418414135 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:51:09,502] Trial 13 finished with value: -618.9508615897482 and parameters: {'embedding_dim': 105, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:51:12,955] Trial 14 finished with value: -455.424109881652 and parameters: {'embedding_dim': 76, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:51:19,481] Trial 15 finished with value: -49.93174910957607 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:51:24,449] Trial 16 finished with value: -631.444549011801 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:51:31,191] Trial 17 finished with value: -138.04542995788165 and parameters: {'embedding_dim': 67, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:51:36,005] Trial 18 finished with value: -765.5005656207985 and parameters: {'embedding_dim': 102, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:51:39,423] Trial 19 finished with value: -354.34740141195834 and parameters: {'embedding_dim': 84, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:51:44,416] Trial 20 finished with value: -532.7813928085118 and parameters: {'embedding_dim': 95, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:51:51,148] Trial 21 finished with value: -329.84995583232393 and parameters: {'embedding_dim': 90, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:51:57,893] Trial 22 finished with value: -205.35175868260603 and parameters: {'embedding_dim': 88, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:52:02,911] Trial 23 finished with value: -131.88439656042593 and parameters: {'embedding_dim': 76, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:52:09,575] Trial 24 finished with value: -251.03693805241798 and parameters: {'embedding_dim': 99, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:52:14,544] Trial 25 finished with value: -57.48807910272625 and parameters: {'embedding_dim': 83, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:52:19,512] Trial 26 finished with value: -111.32934726471561 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:52:26,277] Trial 27 finished with value: -168.55250627734912 and parameters: {'embedding_dim': 108, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:52:31,050] Trial 28 finished with value: -206.49332513621772 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:52:38,145] Trial 29 finished with value: -63.74455746868775 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:52:44,552] Trial 30 finished with value: -199.31859308077898 and parameters: {'embedding_dim': 86, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:52:49,451] Trial 31 finished with value: -144.95222450467364 and parameters: {'embedding_dim': 71, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:52:54,402] Trial 32 finished with value: -301.1908805291248 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:52:59,420] Trial 33 finished with value: -86.45910571686386 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:53:04,395] Trial 34 finished with value: -378.9639141434845 and parameters: {'embedding_dim': 97, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:53:09,183] Trial 35 finished with value: -265.9727950485354 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:53:14,291] Trial 36 finished with value: -86.41934829692909 and parameters: {'embedding_dim': 84, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:53:19,050] Trial 37 finished with value: -199.0057957120263 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:53:24,287] Trial 38 finished with value: -63.53235788685127 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:53:27,694] Trial 39 finished with value: -183.34823460646737 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:53:32,630] Trial 40 finished with value: -205.99273163229054 and parameters: {'embedding_dim': 100, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:53:38,068] Trial 41 finished with value: -115.75285937914532 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:53:43,322] Trial 42 finished with value: -318.62456747141414 and parameters: {'embedding_dim': 88, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:53:48,763] Trial 43 finished with value: -107.49907656237639 and parameters: {'embedding_dim': 94, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:53:54,135] Trial 44 finished with value: -234.84315315905926 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:53:59,430] Trial 45 finished with value: -111.43361144075853 and parameters: {'embedding_dim': 75, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:54:04,395] Trial 46 finished with value: -67.32092192140502 and parameters: {'embedding_dim': 90, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:54:09,686] Trial 47 finished with value: -55.4432711552697 and parameters: {'embedding_dim': 98, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:54:13,021] Trial 48 finished with value: -72.7400181452357 and parameters: {'embedding_dim': 107, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:54:19,418] Trial 49 finished with value: -630.513271965863 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 1 with value: -16.701277526911323.
+[I 2025-12-17 16:54:25,090] A new study created in memory with name: no-name-77e4db52-6049-43eb-89ee-ea6777f49c8c
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_7000_3_seoul_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_7000_3_seoul_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan7000_3_seoul.csv: Class 0=5269 | Class 1=6861
+Saved ../../data/data_oversampled/ctgan7000/ctgan7000_3_seoul.csv: Class 0=5269 | Class 1=6861 | Class 2=15873
+Processing ../../data/data_for_modeling/busan_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/busan_train.csv: Optimizing CTGAN for class 1...
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_7000_3_busan_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_7000_3_busan_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan7000_3_busan.csv: Class 0=6642 | Class 1=6592
+Saved ../../data/data_oversampled/ctgan7000/ctgan7000_3_busan.csv: Class 0=6642 | Class 1=6592 | Class 2=16439
+Processing ../../data/data_for_modeling/daegu_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/daegu_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-17 16:54:36,783] Trial 0 finished with value: -567.3604362909616 and parameters: {'embedding_dim': 387, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 0 with value: -567.3604362909616.
+[I 2025-12-17 16:54:55,380] Trial 1 finished with value: -3822.1893292050086 and parameters: {'embedding_dim': 199, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 0 with value: -567.3604362909616.
+[I 2025-12-17 16:55:06,412] Trial 2 finished with value: -497.67836525661954 and parameters: {'embedding_dim': 382, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 2 with value: -497.67836525661954.
+[I 2025-12-17 16:55:23,013] Trial 3 finished with value: -578.5449149242843 and parameters: {'embedding_dim': 188, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 2 with value: -497.67836525661954.
+[I 2025-12-17 16:55:37,593] Trial 4 finished with value: -1625.6670521974909 and parameters: {'embedding_dim': 252, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -497.67836525661954.
+[I 2025-12-17 16:55:48,272] Trial 5 finished with value: -416.5098705018092 and parameters: {'embedding_dim': 240, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 5 with value: -416.5098705018092.
+[I 2025-12-17 16:55:55,256] Trial 6 finished with value: -375.7247316361628 and parameters: {'embedding_dim': 433, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 6 with value: -375.7247316361628.
+[I 2025-12-17 16:56:03,145] Trial 7 finished with value: -1937.1189256270382 and parameters: {'embedding_dim': 167, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 6 with value: -375.7247316361628.
+[I 2025-12-17 16:56:14,094] Trial 8 finished with value: -758.3966939426213 and parameters: {'embedding_dim': 234, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 6 with value: -375.7247316361628.
+[I 2025-12-17 16:56:27,534] Trial 9 finished with value: -765.4880534086245 and parameters: {'embedding_dim': 374, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 6 with value: -375.7247316361628.
+[I 2025-12-17 16:56:32,239] Trial 10 finished with value: -517.5215191334489 and parameters: {'embedding_dim': 501, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 6 with value: -375.7247316361628.
+[I 2025-12-17 16:56:38,934] Trial 11 finished with value: -894.1832182838197 and parameters: {'embedding_dim': 474, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 6 with value: -375.7247316361628.
+[I 2025-12-17 16:56:44,184] Trial 12 finished with value: -2729.7765574504974 and parameters: {'embedding_dim': 308, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 6 with value: -375.7247316361628.
+[I 2025-12-17 16:56:51,183] Trial 13 finished with value: -726.0968413528716 and parameters: {'embedding_dim': 314, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 6 with value: -375.7247316361628.
+[I 2025-12-17 16:57:01,878] Trial 14 finished with value: -237.54336653637557 and parameters: {'embedding_dim': 439, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 14 with value: -237.54336653637557.
+[I 2025-12-17 16:57:06,945] Trial 15 finished with value: -163.52754077143175 and parameters: {'embedding_dim': 446, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 15 with value: -163.52754077143175.
+[I 2025-12-17 16:57:23,523] Trial 16 finished with value: -224.54570379919346 and parameters: {'embedding_dim': 441, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 15 with value: -163.52754077143175.
+[I 2025-12-17 16:57:39,726] Trial 17 finished with value: -317.8341813681097 and parameters: {'embedding_dim': 511, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 15 with value: -163.52754077143175.
+[I 2025-12-17 16:57:56,004] Trial 18 finished with value: -364.3844054382227 and parameters: {'embedding_dim': 443, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 15 with value: -163.52754077143175.
+[I 2025-12-17 16:58:01,216] Trial 19 finished with value: -1515.8741337852439 and parameters: {'embedding_dim': 350, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 15 with value: -163.52754077143175.
+[I 2025-12-17 16:58:14,680] Trial 20 finished with value: -237.56154963646398 and parameters: {'embedding_dim': 413, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 15 with value: -163.52754077143175.
+[I 2025-12-17 16:58:25,415] Trial 21 finished with value: -211.1596274542001 and parameters: {'embedding_dim': 460, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 15 with value: -163.52754077143175.
+[I 2025-12-17 16:58:41,914] Trial 22 finished with value: -322.7512873567225 and parameters: {'embedding_dim': 468, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 15 with value: -163.52754077143175.
+[I 2025-12-17 16:58:55,479] Trial 23 finished with value: -626.1606396264458 and parameters: {'embedding_dim': 482, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 15 with value: -163.52754077143175.
+[I 2025-12-17 16:59:00,638] Trial 24 finished with value: -1033.058925650314 and parameters: {'embedding_dim': 415, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 15 with value: -163.52754077143175.
+[I 2025-12-17 16:59:15,430] Trial 25 finished with value: -1102.1324451349396 and parameters: {'embedding_dim': 344, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -163.52754077143175.
+[I 2025-12-17 16:59:23,488] Trial 26 finished with value: -417.45357456286985 and parameters: {'embedding_dim': 456, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 15 with value: -163.52754077143175.
+[I 2025-12-17 16:59:37,348] Trial 27 finished with value: -354.56913006763887 and parameters: {'embedding_dim': 410, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 15 with value: -163.52754077143175.
+[I 2025-12-17 16:59:42,407] Trial 28 finished with value: -219.7959419094393 and parameters: {'embedding_dim': 484, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 15 with value: -163.52754077143175.
+[I 2025-12-17 16:59:49,629] Trial 29 finished with value: -1216.7529096918834 and parameters: {'embedding_dim': 496, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 15 with value: -163.52754077143175.
+[I 2025-12-17 16:59:55,192] A new study created in memory with name: no-name-238d1f10-4984-4343-afe1-2a1819ee805c
+[I 2025-12-17 17:00:02,471] Trial 0 finished with value: -45.37032108480602 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -45.37032108480602.
+[I 2025-12-17 17:00:05,861] Trial 1 finished with value: -61.49658152445841 and parameters: {'embedding_dim': 113, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 0 with value: -45.37032108480602.
+[I 2025-12-17 17:00:11,260] Trial 2 finished with value: -4.843314966391603 and parameters: {'embedding_dim': 81, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:00:18,430] Trial 3 finished with value: -12.787391855947087 and parameters: {'embedding_dim': 123, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:00:25,569] Trial 4 finished with value: -48.238908288013846 and parameters: {'embedding_dim': 94, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:00:28,905] Trial 5 finished with value: -169.58620788778242 and parameters: {'embedding_dim': 101, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:00:35,309] Trial 6 finished with value: -14.117688587603315 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:00:40,330] Trial 7 finished with value: -19.356972608672503 and parameters: {'embedding_dim': 121, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:00:45,401] Trial 8 finished with value: -99.8254766920601 and parameters: {'embedding_dim': 66, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:00:48,917] Trial 9 finished with value: -161.04381572950106 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:00:53,974] Trial 10 finished with value: -368.93122092322153 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:00:59,358] Trial 11 finished with value: -22.217352601546885 and parameters: {'embedding_dim': 80, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:01:06,547] Trial 12 finished with value: -96.71419770214732 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:01:11,918] Trial 13 finished with value: -143.79019412488842 and parameters: {'embedding_dim': 127, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:01:19,181] Trial 14 finished with value: -82.35016345073296 and parameters: {'embedding_dim': 79, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:01:24,562] Trial 15 finished with value: -37.71470198031431 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:01:31,121] Trial 16 finished with value: -124.15891055507211 and parameters: {'embedding_dim': 105, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:01:34,640] Trial 17 finished with value: -91.22016660535904 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:01:40,116] Trial 18 finished with value: -153.20894119490268 and parameters: {'embedding_dim': 84, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:01:45,056] Trial 19 finished with value: -71.39223204478968 and parameters: {'embedding_dim': 108, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:01:52,294] Trial 20 finished with value: -58.0205765087345 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:01:58,794] Trial 21 finished with value: -39.646191769636644 and parameters: {'embedding_dim': 87, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:02:05,304] Trial 22 finished with value: -82.75909425953122 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:02:11,927] Trial 23 finished with value: -34.218367072454356 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:02:16,847] Trial 24 finished with value: -60.529798812402305 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:02:23,395] Trial 25 finished with value: -43.07475086923608 and parameters: {'embedding_dim': 72, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:02:30,676] Trial 26 finished with value: -144.83299088789587 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:02:36,058] Trial 27 finished with value: -65.5745557599194 and parameters: {'embedding_dim': 87, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:02:42,852] Trial 28 finished with value: -56.87535023451585 and parameters: {'embedding_dim': 99, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:02:49,416] Trial 29 finished with value: -147.85577007300026 and parameters: {'embedding_dim': 112, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:02:56,738] Trial 30 finished with value: -15.507378557781305 and parameters: {'embedding_dim': 128, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:03:03,990] Trial 31 finished with value: -64.17431238930354 and parameters: {'embedding_dim': 126, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:03:11,261] Trial 32 finished with value: -68.27955282234254 and parameters: {'embedding_dim': 120, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:03:18,548] Trial 33 finished with value: -54.25879411151914 and parameters: {'embedding_dim': 122, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:03:24,045] Trial 34 finished with value: -23.79147336105786 and parameters: {'embedding_dim': 116, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:03:30,806] Trial 35 finished with value: -113.1644065406587 and parameters: {'embedding_dim': 128, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:03:34,326] Trial 36 finished with value: -23.2911518468762 and parameters: {'embedding_dim': 111, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:03:41,133] Trial 37 finished with value: -177.08621014735283 and parameters: {'embedding_dim': 124, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:03:46,581] Trial 38 finished with value: -4.965689353572942 and parameters: {'embedding_dim': 118, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:03:51,981] Trial 39 finished with value: -24.1792134604796 and parameters: {'embedding_dim': 116, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:03:55,344] Trial 40 finished with value: -24.65594750107568 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:04:00,812] Trial 41 finished with value: -11.115016641872085 and parameters: {'embedding_dim': 118, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:04:06,219] Trial 42 finished with value: -83.08937540956953 and parameters: {'embedding_dim': 119, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:04:11,613] Trial 43 finished with value: -45.02278872705836 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:04:17,055] Trial 44 finished with value: -17.449380003347567 and parameters: {'embedding_dim': 116, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:04:22,519] Trial 45 finished with value: -66.51288117859669 and parameters: {'embedding_dim': 107, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:04:27,978] Trial 46 finished with value: -21.993809600318848 and parameters: {'embedding_dim': 123, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:04:32,921] Trial 47 finished with value: -59.73995525399721 and parameters: {'embedding_dim': 97, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:04:38,348] Trial 48 finished with value: -34.64507171177982 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:04:43,744] Trial 49 finished with value: -109.26625037116649 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -4.843314966391603.
+[I 2025-12-17 17:04:49,210] A new study created in memory with name: no-name-1eec9f0b-3fb8-48f3-af55-bbf93829983a
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_7000_3_daegu_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_7000_3_daegu_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan7000_3_daegu.csv: Class 0=5115 | Class 1=6379
+Saved ../../data/data_oversampled/ctgan7000/ctgan7000_3_daegu.csv: Class 0=5115 | Class 1=6379 | Class 2=16913
+Processing ../../data/data_for_modeling/daejeon_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/daejeon_train.csv: Optimizing CTGAN for class 1...
+/opt/conda/envs/py39/lib/python3.9/site-packages/joblib/externals/loky/process_executor.py:752: UserWarning: A worker stopped while some jobs were given to the executor. This can be caused by a too short worker timeout or by a memory leak.
+  warnings.warn(
+[I 2025-12-17 17:05:08,255] Trial 0 finished with value: -769.5732136841211 and parameters: {'embedding_dim': 465, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 0 with value: -769.5732136841211.
+[I 2025-12-17 17:05:27,826] Trial 1 finished with value: -1311.3436250780192 and parameters: {'embedding_dim': 372, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 0 with value: -769.5732136841211.
+[I 2025-12-17 17:06:37,303] Trial 2 finished with value: -1507.1707793167025 and parameters: {'embedding_dim': 261, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 0 with value: -769.5732136841211.
+[I 2025-12-17 17:07:33,589] Trial 3 finished with value: -805.4282337462653 and parameters: {'embedding_dim': 465, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 0 with value: -769.5732136841211.
+[I 2025-12-17 17:08:20,350] Trial 4 finished with value: -577.8017666851255 and parameters: {'embedding_dim': 340, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -577.8017666851255.
+[I 2025-12-17 17:08:43,792] Trial 5 finished with value: -422.08105768686977 and parameters: {'embedding_dim': 324, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 5 with value: -422.08105768686977.
+[I 2025-12-17 17:09:40,299] Trial 6 finished with value: -531.9427065373809 and parameters: {'embedding_dim': 378, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 5 with value: -422.08105768686977.
+[I 2025-12-17 17:09:57,668] Trial 7 finished with value: -467.38299591385686 and parameters: {'embedding_dim': 280, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 5 with value: -422.08105768686977.
+[I 2025-12-17 17:10:08,975] Trial 8 finished with value: -1479.9977969985744 and parameters: {'embedding_dim': 377, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 5 with value: -422.08105768686977.
+[I 2025-12-17 17:10:23,256] Trial 9 finished with value: -1713.1445972403828 and parameters: {'embedding_dim': 452, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 5 with value: -422.08105768686977.
+[I 2025-12-17 17:10:37,671] Trial 10 finished with value: -1496.7776450118736 and parameters: {'embedding_dim': 147, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 5 with value: -422.08105768686977.
+[I 2025-12-17 17:10:52,052] Trial 11 finished with value: -264.260176277027 and parameters: {'embedding_dim': 252, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 11 with value: -264.260176277027.
+[I 2025-12-17 17:11:06,909] Trial 12 finished with value: -2279.3125605987443 and parameters: {'embedding_dim': 204, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 11 with value: -264.260176277027.
+[I 2025-12-17 17:11:28,825] Trial 13 finished with value: -298.5444297471502 and parameters: {'embedding_dim': 243, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 11 with value: -264.260176277027.
+[I 2025-12-17 17:11:52,171] Trial 14 finished with value: -461.0599189461682 and parameters: {'embedding_dim': 219, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 11 with value: -264.260176277027.
+[I 2025-12-17 17:12:16,037] Trial 15 finished with value: -609.21962989145 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 11 with value: -264.260176277027.
+[I 2025-12-17 17:12:39,649] Trial 16 finished with value: -2216.2280764308807 and parameters: {'embedding_dim': 218, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 11 with value: -264.260176277027.
+[I 2025-12-17 17:12:56,771] Trial 17 finished with value: -1892.3852333280927 and parameters: {'embedding_dim': 268, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 11 with value: -264.260176277027.
+[I 2025-12-17 17:13:18,033] Trial 18 finished with value: -1103.6865942476118 and parameters: {'embedding_dim': 183, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 11 with value: -264.260176277027.
+[I 2025-12-17 17:13:34,972] Trial 19 finished with value: -425.7469016270846 and parameters: {'embedding_dim': 289, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 11 with value: -264.260176277027.
+[I 2025-12-17 17:13:58,309] Trial 20 finished with value: -802.4661937840611 and parameters: {'embedding_dim': 242, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 11 with value: -264.260176277027.
+[I 2025-12-17 17:14:21,858] Trial 21 finished with value: -432.60143439159344 and parameters: {'embedding_dim': 321, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 11 with value: -264.260176277027.
+[I 2025-12-17 17:14:44,330] Trial 22 finished with value: -504.8539082674268 and parameters: {'embedding_dim': 319, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 11 with value: -264.260176277027.
+[I 2025-12-17 17:15:02,429] Trial 23 finished with value: -2180.115960129647 and parameters: {'embedding_dim': 423, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 11 with value: -264.260176277027.
+[I 2025-12-17 17:15:41,742] Trial 24 finished with value: -499.27630251487653 and parameters: {'embedding_dim': 306, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -264.260176277027.
+[I 2025-12-17 17:15:57,638] Trial 25 finished with value: -729.4974811365512 and parameters: {'embedding_dim': 178, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 11 with value: -264.260176277027.
+[I 2025-12-17 17:16:36,528] Trial 26 finished with value: -337.33539027787253 and parameters: {'embedding_dim': 346, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -264.260176277027.
+[I 2025-12-17 17:17:05,252] Trial 27 finished with value: -263.24858069376023 and parameters: {'embedding_dim': 247, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 27 with value: -263.24858069376023.
+[I 2025-12-17 17:17:36,468] Trial 28 finished with value: -482.17218294222533 and parameters: {'embedding_dim': 244, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 27 with value: -263.24858069376023.
+[I 2025-12-17 17:18:05,860] Trial 29 finished with value: -759.385041984038 and parameters: {'embedding_dim': 180, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 27 with value: -263.24858069376023.
+[I 2025-12-17 17:18:36,982] A new study created in memory with name: no-name-76410745-9456-489f-919d-2022d102206f
+[I 2025-12-17 17:18:40,169] Trial 0 finished with value: -4.847504309102946 and parameters: {'embedding_dim': 108, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -4.847504309102946.
+[I 2025-12-17 17:18:43,576] Trial 1 finished with value: -1.2576471415433854 and parameters: {'embedding_dim': 117, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:18:48,874] Trial 2 finished with value: -227.0458069472635 and parameters: {'embedding_dim': 91, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:18:52,083] Trial 3 finished with value: -587.2087258298524 and parameters: {'embedding_dim': 76, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:18:57,416] Trial 4 finished with value: -55.94567079164854 and parameters: {'embedding_dim': 66, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:19:03,511] Trial 5 finished with value: -449.24005387861365 and parameters: {'embedding_dim': 67, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:19:07,263] Trial 6 finished with value: -230.5680772944823 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:19:10,687] Trial 7 finished with value: -200.6482320736128 and parameters: {'embedding_dim': 113, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:19:15,782] Trial 8 finished with value: -48.66418561536127 and parameters: {'embedding_dim': 75, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:19:22,406] Trial 9 finished with value: -124.31692693317801 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:19:30,169] Trial 10 finished with value: -69.75169186050906 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:19:33,452] Trial 11 finished with value: -269.08839569404324 and parameters: {'embedding_dim': 110, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:19:38,162] Trial 12 finished with value: -105.79163387829064 and parameters: {'embedding_dim': 112, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:19:46,130] Trial 13 finished with value: -60.8650475937318 and parameters: {'embedding_dim': 125, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:19:49,369] Trial 14 finished with value: -221.36332774891977 and parameters: {'embedding_dim': 102, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:19:54,325] Trial 15 finished with value: -249.14646138898013 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:19:57,512] Trial 16 finished with value: -340.6527263235025 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:20:05,533] Trial 17 finished with value: -42.0836663574741 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:20:11,841] Trial 18 finished with value: -20.52195807390845 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:20:15,151] Trial 19 finished with value: -17.18768904370716 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:20:19,309] Trial 20 finished with value: -71.3732361984139 and parameters: {'embedding_dim': 119, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:20:22,699] Trial 21 finished with value: -41.1370327666723 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:20:26,044] Trial 22 finished with value: -19.155575238573956 and parameters: {'embedding_dim': 107, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:20:31,307] Trial 23 finished with value: -77.05452640568902 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:20:34,810] Trial 24 finished with value: -97.26485373742489 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:20:41,343] Trial 25 finished with value: -11.780685549472093 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:20:46,375] Trial 26 finished with value: -127.27014223429113 and parameters: {'embedding_dim': 98, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:20:52,781] Trial 27 finished with value: -70.18842332887422 and parameters: {'embedding_dim': 115, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:20:58,140] Trial 28 finished with value: -101.11121979746724 and parameters: {'embedding_dim': 105, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:21:03,171] Trial 29 finished with value: -188.77025854156463 and parameters: {'embedding_dim': 122, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:21:10,369] Trial 30 finished with value: -43.76429080683479 and parameters: {'embedding_dim': 89, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:21:13,648] Trial 31 finished with value: -457.46263418679786 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:21:16,970] Trial 32 finished with value: -30.174237626271605 and parameters: {'embedding_dim': 89, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:21:20,391] Trial 33 finished with value: -20.309288605161896 and parameters: {'embedding_dim': 81, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:21:25,487] Trial 34 finished with value: -37.22826496580319 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:21:30,346] Trial 35 finished with value: -72.93386855203303 and parameters: {'embedding_dim': 71, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:21:33,581] Trial 36 finished with value: -7.587343353009796 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:21:37,246] Trial 37 finished with value: -173.9817044372558 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:21:42,062] Trial 38 finished with value: -50.39154614381549 and parameters: {'embedding_dim': 99, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:21:45,381] Trial 39 finished with value: -35.624336521121194 and parameters: {'embedding_dim': 108, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:21:48,520] Trial 40 finished with value: -49.175176280649765 and parameters: {'embedding_dim': 116, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:21:51,814] Trial 41 finished with value: -70.22656944066601 and parameters: {'embedding_dim': 88, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -1.2576471415433854.
+[I 2025-12-17 17:21:55,118] Trial 42 finished with value: -0.14530457631510396 and parameters: {'embedding_dim': 77, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 42 with value: -0.14530457631510396.
+[I 2025-12-17 17:21:58,412] Trial 43 finished with value: -226.92978418291528 and parameters: {'embedding_dim': 65, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 42 with value: -0.14530457631510396.
+[I 2025-12-17 17:22:01,700] Trial 44 finished with value: -133.3257416489413 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 42 with value: -0.14530457631510396.
+[I 2025-12-17 17:22:04,987] Trial 45 finished with value: -21.2581928229118 and parameters: {'embedding_dim': 77, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 42 with value: -0.14530457631510396.
+[I 2025-12-17 17:22:08,234] Trial 46 finished with value: -436.94130729298433 and parameters: {'embedding_dim': 81, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 42 with value: -0.14530457631510396.
+[I 2025-12-17 17:22:13,256] Trial 47 finished with value: -16.21570399280582 and parameters: {'embedding_dim': 73, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 42 with value: -0.14530457631510396.
+[I 2025-12-17 17:22:16,535] Trial 48 finished with value: -535.2669827622781 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 42 with value: -0.14530457631510396.
+[I 2025-12-17 17:22:20,203] Trial 49 finished with value: -405.0210892624173 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 42 with value: -0.14530457631510396.
+[I 2025-12-17 17:22:23,741] A new study created in memory with name: no-name-b311081e-37dc-4708-8031-53eae981e52c
+[I 2025-12-17 17:22:40,370] Trial 0 finished with value: -1024.3575560118747 and parameters: {'embedding_dim': 422, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 0 with value: -1024.3575560118747.
+[I 2025-12-17 17:23:27,832] Trial 1 finished with value: -1352.1566598928162 and parameters: {'embedding_dim': 403, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 0 with value: -1024.3575560118747.
+[I 2025-12-17 17:23:38,692] Trial 2 finished with value: -830.4027751050203 and parameters: {'embedding_dim': 504, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 2 with value: -830.4027751050203.
+[I 2025-12-17 17:24:16,828] Trial 3 finished with value: -352.794952839144 and parameters: {'embedding_dim': 140, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 3 with value: -352.794952839144.
+[I 2025-12-17 17:24:27,603] Trial 4 finished with value: -861.8761938517889 and parameters: {'embedding_dim': 384, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 3 with value: -352.794952839144.
+[I 2025-12-17 17:24:51,144] Trial 5 finished with value: -271.62929188516625 and parameters: {'embedding_dim': 269, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 5 with value: -271.62929188516625.
+[I 2025-12-17 17:25:07,874] Trial 6 finished with value: -600.9277033947322 and parameters: {'embedding_dim': 460, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 5 with value: -271.62929188516625.
+[I 2025-12-17 17:25:26,669] Trial 7 finished with value: -628.6056436586321 and parameters: {'embedding_dim': 159, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 5 with value: -271.62929188516625.
+[I 2025-12-17 17:25:41,510] Trial 8 finished with value: -914.5824209985898 and parameters: {'embedding_dim': 317, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 5 with value: -271.62929188516625.
+[I 2025-12-17 17:26:00,594] Trial 9 finished with value: -305.0484142250919 and parameters: {'embedding_dim': 282, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 5 with value: -271.62929188516625.
+[I 2025-12-17 17:26:21,237] Trial 10 finished with value: -627.7256558940587 and parameters: {'embedding_dim': 235, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 5 with value: -271.62929188516625.
+[I 2025-12-17 17:26:50,609] Trial 11 finished with value: -739.5655279996895 and parameters: {'embedding_dim': 278, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 5 with value: -271.62929188516625.
+[I 2025-12-17 17:27:09,757] Trial 12 finished with value: -395.7197361709443 and parameters: {'embedding_dim': 264, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 5 with value: -271.62929188516625.
+[I 2025-12-17 17:27:34,273] Trial 13 finished with value: -92.3992282319681 and parameters: {'embedding_dim': 210, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 13 with value: -92.3992282319681.
+[I 2025-12-17 17:27:58,658] Trial 14 finished with value: -1056.1455700089139 and parameters: {'embedding_dim': 201, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 13 with value: -92.3992282319681.
+[I 2025-12-17 17:28:17,665] Trial 15 finished with value: -451.11083757172844 and parameters: {'embedding_dim': 208, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 13 with value: -92.3992282319681.
+[I 2025-12-17 17:28:41,184] Trial 16 finished with value: -2411.501966485572 and parameters: {'embedding_dim': 353, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 13 with value: -92.3992282319681.
+[I 2025-12-17 17:28:56,046] Trial 17 finished with value: -986.489734728225 and parameters: {'embedding_dim': 182, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 13 with value: -92.3992282319681.
+[I 2025-12-17 17:29:44,275] Trial 18 finished with value: -1104.7376397250673 and parameters: {'embedding_dim': 323, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 13 with value: -92.3992282319681.
+[I 2025-12-17 17:30:05,193] Trial 19 finished with value: -374.90853180444276 and parameters: {'embedding_dim': 251, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 13 with value: -92.3992282319681.
+[I 2025-12-17 17:30:25,083] Trial 20 finished with value: -952.5042421298499 and parameters: {'embedding_dim': 129, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 13 with value: -92.3992282319681.
+[I 2025-12-17 17:30:44,635] Trial 21 finished with value: -647.7520788880184 and parameters: {'embedding_dim': 301, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 13 with value: -92.3992282319681.
+[I 2025-12-17 17:31:03,815] Trial 22 finished with value: -575.7472892573313 and parameters: {'embedding_dim': 221, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 13 with value: -92.3992282319681.
+[I 2025-12-17 17:31:52,151] Trial 23 finished with value: -695.7960690702781 and parameters: {'embedding_dim': 283, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 13 with value: -92.3992282319681.
+[I 2025-12-17 17:32:20,444] Trial 24 finished with value: -1000.6458626180593 and parameters: {'embedding_dim': 361, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 13 with value: -92.3992282319681.
+[I 2025-12-17 17:32:36,958] Trial 25 finished with value: -1082.1847913759564 and parameters: {'embedding_dim': 184, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 13 with value: -92.3992282319681.
+[I 2025-12-17 17:33:05,104] Trial 26 finished with value: -258.0174609418343 and parameters: {'embedding_dim': 241, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 13 with value: -92.3992282319681.
+[I 2025-12-17 17:33:29,982] Trial 27 finished with value: -497.95006266702535 and parameters: {'embedding_dim': 245, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 13 with value: -92.3992282319681.
+[I 2025-12-17 17:33:57,469] Trial 28 finished with value: -256.7471247679324 and parameters: {'embedding_dim': 165, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 13 with value: -92.3992282319681.
+[I 2025-12-17 17:34:25,824] Trial 29 finished with value: -435.7039256109186 and parameters: {'embedding_dim': 160, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 13 with value: -92.3992282319681.
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_7000_3_daejeon_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_7000_3_daejeon_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan7000_3_daejeon.csv: Class 0=5815 | Class 1=6319
+Saved ../../data/data_oversampled/ctgan7000/ctgan7000_3_daejeon.csv: Class 0=5815 | Class 1=6319 | Class 2=15784
+Processing ../../data/data_for_modeling/gwangju_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/gwangju_train.csv: Optimizing CTGAN for class 1...
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_7000_3_gwangju_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_7000_3_gwangju_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan7000_3_gwangju.csv: Class 0=5943 | Class 1=6475
+Saved ../../data/data_oversampled/ctgan7000/ctgan7000_3_gwangju.csv: Class 0=5943 | Class 1=6475 | Class 2=16144
+
+=== Processing 10000 samples ===
+Running ctgan_sample_10000_1.py...
+[I 2025-12-17 17:34:53,078] A new study created in memory with name: no-name-3b8c956c-6d2d-4009-ad65-e72166f85761
+[I 2025-12-17 17:35:07,375] Trial 0 finished with value: -49.22201429332661 and parameters: {'embedding_dim': 112, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -49.22201429332661.
+[I 2025-12-17 17:35:30,391] Trial 1 finished with value: -22.747949068724004 and parameters: {'embedding_dim': 127, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -22.747949068724004.
+[I 2025-12-17 17:35:36,923] Trial 2 finished with value: -492.33546865992116 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -22.747949068724004.
+[I 2025-12-17 17:35:40,816] Trial 3 finished with value: -19.93195239088434 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 3 with value: -19.93195239088434.
+[I 2025-12-17 17:35:48,632] Trial 4 finished with value: -9.30205952226806 and parameters: {'embedding_dim': 89, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -9.30205952226806.
+[I 2025-12-17 17:35:58,639] Trial 5 finished with value: -28.751137254327 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -9.30205952226806.
+[I 2025-12-17 17:36:04,356] Trial 6 finished with value: -5.519876522212156 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 6 with value: -5.519876522212156.
+[I 2025-12-17 17:36:35,613] Trial 7 finished with value: -79.64991338462482 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 6 with value: -5.519876522212156.
+[I 2025-12-17 17:36:42,135] Trial 8 finished with value: -17.6498778368646 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 6 with value: -5.519876522212156.
+[I 2025-12-17 17:37:13,231] Trial 9 finished with value: -85.11959493497018 and parameters: {'embedding_dim': 117, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 6 with value: -5.519876522212156.
+[I 2025-12-17 17:37:18,961] Trial 10 finished with value: -9.210400002273394 and parameters: {'embedding_dim': 66, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 6 with value: -5.519876522212156.
+[I 2025-12-17 17:37:24,743] Trial 11 finished with value: -2.77332883658777 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -2.77332883658777.
+[I 2025-12-17 17:37:30,490] Trial 12 finished with value: -51.77764480889331 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -2.77332883658777.
+[I 2025-12-17 17:37:36,226] Trial 13 finished with value: -33.88489779883267 and parameters: {'embedding_dim': 80, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -2.77332883658777.
+[I 2025-12-17 17:37:42,167] Trial 14 finished with value: -3.1460862959286082 and parameters: {'embedding_dim': 71, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -2.77332883658777.
+[I 2025-12-17 17:37:46,060] Trial 15 finished with value: -50.32538729371511 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 11 with value: -2.77332883658777.
+[I 2025-12-17 17:37:51,866] Trial 16 finished with value: -11.657786739704308 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -2.77332883658777.
+[I 2025-12-17 17:37:59,743] Trial 17 finished with value: -11.722230235579586 and parameters: {'embedding_dim': 100, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 11 with value: -2.77332883658777.
+[I 2025-12-17 17:38:05,519] Trial 18 finished with value: -2.072734482318714 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -2.072734482318714.
+[I 2025-12-17 17:38:20,505] Trial 19 finished with value: -104.0425301417662 and parameters: {'embedding_dim': 84, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 18 with value: -2.072734482318714.
+[I 2025-12-17 17:38:26,304] Trial 20 finished with value: -28.706199114418226 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -2.072734482318714.
+[I 2025-12-17 17:38:32,024] Trial 21 finished with value: -205.56653006421598 and parameters: {'embedding_dim': 71, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -2.072734482318714.
+[I 2025-12-17 17:38:37,776] Trial 22 finished with value: -0.5260007033847117 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 22 with value: -0.5260007033847117.
+[I 2025-12-17 17:38:43,492] Trial 23 finished with value: -50.04594466676612 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 22 with value: -0.5260007033847117.
+[I 2025-12-17 17:38:49,235] Trial 24 finished with value: -48.8870375346162 and parameters: {'embedding_dim': 70, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 22 with value: -0.5260007033847117.
+[I 2025-12-17 17:38:54,974] Trial 25 finished with value: -0.4360448851012551 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:39:02,652] Trial 26 finished with value: -1.7605263423699475 and parameters: {'embedding_dim': 84, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:39:10,337] Trial 27 finished with value: -103.74967136223934 and parameters: {'embedding_dim': 86, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:39:23,695] Trial 28 finished with value: -28.23787685412253 and parameters: {'embedding_dim': 95, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:39:54,959] Trial 29 finished with value: -89.74203531086896 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:40:08,455] Trial 30 finished with value: -60.84292524461791 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:40:14,201] Trial 31 finished with value: -38.167660018299856 and parameters: {'embedding_dim': 77, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:40:20,010] Trial 32 finished with value: -53.96732441820222 and parameters: {'embedding_dim': 75, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:40:25,745] Trial 33 finished with value: -104.68464915790211 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:40:29,674] Trial 34 finished with value: -73.24195004029319 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:40:35,430] Trial 35 finished with value: -53.20981137202826 and parameters: {'embedding_dim': 76, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:40:41,291] Trial 36 finished with value: -276.63012517940643 and parameters: {'embedding_dim': 88, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:40:48,014] Trial 37 finished with value: -1.520673945904865 and parameters: {'embedding_dim': 68, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:40:54,653] Trial 38 finished with value: -66.65142420419251 and parameters: {'embedding_dim': 68, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:41:01,226] Trial 39 finished with value: -5.727108778288758 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:41:07,805] Trial 40 finished with value: -92.76127353220387 and parameters: {'embedding_dim': 126, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:41:21,358] Trial 41 finished with value: -151.79739078778337 and parameters: {'embedding_dim': 75, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:41:36,159] Trial 42 finished with value: -624.9905184766379 and parameters: {'embedding_dim': 67, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:41:46,359] Trial 43 finished with value: -79.31249257754837 and parameters: {'embedding_dim': 81, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:41:54,045] Trial 44 finished with value: -173.0325797862142 and parameters: {'embedding_dim': 67, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:42:04,109] Trial 45 finished with value: -114.10658549704914 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:42:07,962] Trial 46 finished with value: -142.4509933940463 and parameters: {'embedding_dim': 74, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:42:30,858] Trial 47 finished with value: -43.928835271666074 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:42:36,894] Trial 48 finished with value: -3.1065943158188443 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:42:44,778] Trial 49 finished with value: -1.3449277979615066 and parameters: {'embedding_dim': 70, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 25 with value: -0.4360448851012551.
+[I 2025-12-17 17:42:50,674] A new study created in memory with name: no-name-54742274-78e4-46ff-88a2-60b6cc7cca2e
+Using device: cuda
+Processing ../../data/data_for_modeling/incheon_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/incheon_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-17 17:43:12,848] Trial 0 finished with value: -359.40022721049775 and parameters: {'embedding_dim': 163, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 0 with value: -359.40022721049775.
+[I 2025-12-17 17:44:28,098] Trial 1 finished with value: -2653.084327948987 and parameters: {'embedding_dim': 259, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -359.40022721049775.
+[I 2025-12-17 17:45:41,460] Trial 2 finished with value: -1613.4303299178487 and parameters: {'embedding_dim': 224, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -359.40022721049775.
+[I 2025-12-17 17:47:15,771] Trial 3 finished with value: -182.0759203861932 and parameters: {'embedding_dim': 282, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 3 with value: -182.0759203861932.
+[I 2025-12-17 17:47:46,314] Trial 4 finished with value: -336.5161174096217 and parameters: {'embedding_dim': 355, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 3 with value: -182.0759203861932.
+[I 2025-12-17 17:48:00,346] Trial 5 finished with value: -636.8759186446061 and parameters: {'embedding_dim': 270, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 3 with value: -182.0759203861932.
+[I 2025-12-17 17:48:45,349] Trial 6 finished with value: -144.96909226588377 and parameters: {'embedding_dim': 289, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 6 with value: -144.96909226588377.
+[I 2025-12-17 17:49:22,095] Trial 7 finished with value: -460.84596165670473 and parameters: {'embedding_dim': 504, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 6 with value: -144.96909226588377.
+[I 2025-12-17 17:50:30,709] Trial 8 finished with value: -294.8703860423357 and parameters: {'embedding_dim': 343, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 6 with value: -144.96909226588377.
+[I 2025-12-17 17:50:56,214] Trial 9 finished with value: -342.7654813836935 and parameters: {'embedding_dim': 323, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 6 with value: -144.96909226588377.
+[I 2025-12-17 17:52:02,997] Trial 10 finished with value: -170.79531990371214 and parameters: {'embedding_dim': 429, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 6 with value: -144.96909226588377.
+[I 2025-12-17 17:53:10,979] Trial 11 finished with value: -49.67487770080678 and parameters: {'embedding_dim': 436, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 11 with value: -49.67487770080678.
+[I 2025-12-17 17:54:08,013] Trial 12 finished with value: -673.5085581263957 and parameters: {'embedding_dim': 423, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 11 with value: -49.67487770080678.
+[I 2025-12-17 17:54:42,177] Trial 13 finished with value: -296.801639644428 and parameters: {'embedding_dim': 413, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 11 with value: -49.67487770080678.
+[I 2025-12-17 17:55:15,349] Trial 14 finished with value: -349.04321854653335 and parameters: {'embedding_dim': 485, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 11 with value: -49.67487770080678.
+[I 2025-12-17 17:56:22,483] Trial 15 finished with value: -82.40430047044632 and parameters: {'embedding_dim': 188, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 11 with value: -49.67487770080678.
+[I 2025-12-17 17:57:34,630] Trial 16 finished with value: -213.60559214776373 and parameters: {'embedding_dim': 164, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 11 with value: -49.67487770080678.
+[I 2025-12-17 17:58:44,649] Trial 17 finished with value: -51.2760658295499 and parameters: {'embedding_dim': 377, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 11 with value: -49.67487770080678.
+[I 2025-12-17 17:59:44,143] Trial 18 finished with value: -138.8669376525316 and parameters: {'embedding_dim': 389, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 11 with value: -49.67487770080678.
+[I 2025-12-17 18:00:59,758] Trial 19 finished with value: -1031.1788367302624 and parameters: {'embedding_dim': 445, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 11 with value: -49.67487770080678.
+[I 2025-12-17 18:01:58,517] Trial 20 finished with value: -98.89919453685741 and parameters: {'embedding_dim': 377, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 11 with value: -49.67487770080678.
+[I 2025-12-17 18:03:11,611] Trial 21 finished with value: -875.9200835284524 and parameters: {'embedding_dim': 217, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 11 with value: -49.67487770080678.
+[I 2025-12-17 18:04:29,139] Trial 22 finished with value: -824.1030395346584 and parameters: {'embedding_dim': 133, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 11 with value: -49.67487770080678.
+[I 2025-12-17 18:05:46,104] Trial 23 finished with value: -178.29669505136047 and parameters: {'embedding_dim': 457, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 11 with value: -49.67487770080678.
+[I 2025-12-17 18:06:44,353] Trial 24 finished with value: -404.06464361179945 and parameters: {'embedding_dim': 391, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 11 with value: -49.67487770080678.
+[I 2025-12-17 18:08:00,499] Trial 25 finished with value: -84.24762308827037 and parameters: {'embedding_dim': 461, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 11 with value: -49.67487770080678.
+[I 2025-12-17 18:09:03,370] Trial 26 finished with value: -135.5472219400864 and parameters: {'embedding_dim': 357, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 11 with value: -49.67487770080678.
+[I 2025-12-17 18:10:16,588] Trial 27 finished with value: -250.96280411205163 and parameters: {'embedding_dim': 309, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 11 with value: -49.67487770080678.
+[I 2025-12-17 18:11:55,559] Trial 28 finished with value: -108.38501711551959 and parameters: {'embedding_dim': 401, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 11 with value: -49.67487770080678.
+[I 2025-12-17 18:12:32,258] Trial 29 finished with value: -490.43746076540083 and parameters: {'embedding_dim': 183, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 11 with value: -49.67487770080678.
+[I 2025-12-17 18:13:41,220] A new study created in memory with name: no-name-e15daebe-8139-4c15-b411-bf3cb721a8aa
+[I 2025-12-17 18:13:48,282] Trial 0 finished with value: -39.96006923848732 and parameters: {'embedding_dim': 108, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -39.96006923848732.
+[I 2025-12-17 18:13:51,688] Trial 1 finished with value: -84.77667299588586 and parameters: {'embedding_dim': 117, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -39.96006923848732.
+[I 2025-12-17 18:13:54,821] Trial 2 finished with value: -8.011113339161273 and parameters: {'embedding_dim': 83, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:13:58,094] Trial 3 finished with value: -333.34462088522025 and parameters: {'embedding_dim': 83, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:14:04,875] Trial 4 finished with value: -39.28276907813935 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:14:08,082] Trial 5 finished with value: -148.40984225614955 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:14:14,593] Trial 6 finished with value: -29.46221075817879 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:14:19,488] Trial 7 finished with value: -95.34845970863843 and parameters: {'embedding_dim': 112, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:14:26,587] Trial 8 finished with value: -82.05403022208714 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:14:29,693] Trial 9 finished with value: -100.38399198551906 and parameters: {'embedding_dim': 114, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:14:34,502] Trial 10 finished with value: -44.468431986941425 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:14:39,302] Trial 11 finished with value: -59.3304408183923 and parameters: {'embedding_dim': 87, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:14:45,747] Trial 12 finished with value: -68.76512547113026 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:14:50,662] Trial 13 finished with value: -28.191157753495023 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:14:55,441] Trial 14 finished with value: -97.50918321676471 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:14:58,608] Trial 15 finished with value: -84.75650433159342 and parameters: {'embedding_dim': 127, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:15:03,332] Trial 16 finished with value: -78.42444113657176 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:15:06,562] Trial 17 finished with value: -150.39293858542942 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:15:11,435] Trial 18 finished with value: -31.002933703199524 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:15:16,805] Trial 19 finished with value: -42.20031024428078 and parameters: {'embedding_dim': 80, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:15:19,935] Trial 20 finished with value: -142.44902490419992 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:15:26,373] Trial 21 finished with value: -122.3173628448265 and parameters: {'embedding_dim': 94, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:15:32,857] Trial 22 finished with value: -33.3502467349031 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:15:39,292] Trial 23 finished with value: -11.422023283070619 and parameters: {'embedding_dim': 70, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:15:44,062] Trial 24 finished with value: -37.46622550413048 and parameters: {'embedding_dim': 70, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:15:48,832] Trial 25 finished with value: -46.78790776920904 and parameters: {'embedding_dim': 79, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:15:53,618] Trial 26 finished with value: -87.56209379643877 and parameters: {'embedding_dim': 71, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:15:56,733] Trial 27 finished with value: -16.289077010129777 and parameters: {'embedding_dim': 68, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:15:59,917] Trial 28 finished with value: -34.48486028260494 and parameters: {'embedding_dim': 68, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:16:03,370] Trial 29 finished with value: -64.35597800170588 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:16:06,751] Trial 30 finished with value: -64.5886357424697 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:16:09,916] Trial 31 finished with value: -39.72293792718092 and parameters: {'embedding_dim': 67, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:16:16,321] Trial 32 finished with value: -41.74851041002282 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:16:19,475] Trial 33 finished with value: -50.279961908392366 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 2 with value: -8.011113339161273.
+[I 2025-12-17 18:16:22,676] Trial 34 finished with value: -3.188320199070745 and parameters: {'embedding_dim': 68, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 34 with value: -3.188320199070745.
+[I 2025-12-17 18:16:26,015] Trial 35 finished with value: -105.09962465482398 and parameters: {'embedding_dim': 68, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 34 with value: -3.188320199070745.
+[I 2025-12-17 18:16:29,293] Trial 36 finished with value: -40.4848932933057 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 34 with value: -3.188320199070745.
+[I 2025-12-17 18:16:32,540] Trial 37 finished with value: -1.9716778952435086 and parameters: {'embedding_dim': 77, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 37 with value: -1.9716778952435086.
+[I 2025-12-17 18:16:35,793] Trial 38 finished with value: -336.9877237784035 and parameters: {'embedding_dim': 77, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 37 with value: -1.9716778952435086.
+[I 2025-12-17 18:16:39,027] Trial 39 finished with value: -178.10346437156534 and parameters: {'embedding_dim': 83, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 37 with value: -1.9716778952435086.
+[I 2025-12-17 18:16:42,235] Trial 40 finished with value: -136.53991686819384 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 37 with value: -1.9716778952435086.
+[I 2025-12-17 18:16:45,456] Trial 41 finished with value: -28.63442589368733 and parameters: {'embedding_dim': 71, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 37 with value: -1.9716778952435086.
+[I 2025-12-17 18:16:48,685] Trial 42 finished with value: -1.724242554818303 and parameters: {'embedding_dim': 68, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 42 with value: -1.724242554818303.
+[I 2025-12-17 18:16:51,890] Trial 43 finished with value: -188.14962279027839 and parameters: {'embedding_dim': 77, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 42 with value: -1.724242554818303.
+[I 2025-12-17 18:16:55,116] Trial 44 finished with value: -86.60129142277081 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 42 with value: -1.724242554818303.
+[I 2025-12-17 18:16:58,345] Trial 45 finished with value: -56.03528933111559 and parameters: {'embedding_dim': 71, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 42 with value: -1.724242554818303.
+[I 2025-12-17 18:17:01,552] Trial 46 finished with value: -241.50187363945247 and parameters: {'embedding_dim': 66, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 42 with value: -1.724242554818303.
+[I 2025-12-17 18:17:04,937] Trial 47 finished with value: -23.470276334444623 and parameters: {'embedding_dim': 73, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 42 with value: -1.724242554818303.
+[I 2025-12-17 18:17:11,670] Trial 48 finished with value: -21.419545891452724 and parameters: {'embedding_dim': 81, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 42 with value: -1.724242554818303.
+[I 2025-12-17 18:17:16,546] Trial 49 finished with value: -124.04575098882938 and parameters: {'embedding_dim': 118, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 42 with value: -1.724242554818303.
+[I 2025-12-17 18:17:19,967] A new study created in memory with name: no-name-cc5cc4e9-04b6-4c0f-95cf-499c175b3cce
+[I 2025-12-17 18:17:34,389] Trial 0 finished with value: -1415.1650893321128 and parameters: {'embedding_dim': 479, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 0 with value: -1415.1650893321128.
+[I 2025-12-17 18:18:03,502] Trial 1 finished with value: -68.91751813871862 and parameters: {'embedding_dim': 282, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 1 with value: -68.91751813871862.
+[I 2025-12-17 18:18:45,272] Trial 2 finished with value: -452.5595318176431 and parameters: {'embedding_dim': 412, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 1 with value: -68.91751813871862.
+[I 2025-12-17 18:19:50,739] Trial 3 finished with value: -21.65559039958045 and parameters: {'embedding_dim': 187, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 3 with value: -21.65559039958045.
+[I 2025-12-17 18:20:02,326] Trial 4 finished with value: -1045.3114728983032 and parameters: {'embedding_dim': 469, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 3 with value: -21.65559039958045.
+[I 2025-12-17 18:21:21,918] Trial 5 finished with value: -54.49438177376361 and parameters: {'embedding_dim': 268, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 3 with value: -21.65559039958045.
+[I 2025-12-17 18:21:38,269] Trial 6 finished with value: -557.9834576944124 and parameters: {'embedding_dim': 383, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 3 with value: -21.65559039958045.
+[I 2025-12-17 18:22:30,879] Trial 7 finished with value: -247.2889020333135 and parameters: {'embedding_dim': 415, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 3 with value: -21.65559039958045.
+[I 2025-12-17 18:22:48,518] Trial 8 finished with value: -486.27152865273376 and parameters: {'embedding_dim': 309, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 3 with value: -21.65559039958045.
+[I 2025-12-17 18:22:56,766] Trial 9 finished with value: -908.6193666598774 and parameters: {'embedding_dim': 502, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 3 with value: -21.65559039958045.
+[I 2025-12-17 18:24:03,281] Trial 10 finished with value: -39.266646724841564 and parameters: {'embedding_dim': 158, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 3 with value: -21.65559039958045.
+[I 2025-12-17 18:25:09,274] Trial 11 finished with value: -435.1154664315105 and parameters: {'embedding_dim': 139, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 3 with value: -21.65559039958045.
+[I 2025-12-17 18:26:15,242] Trial 12 finished with value: -638.4913121594241 and parameters: {'embedding_dim': 141, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 3 with value: -21.65559039958045.
+[I 2025-12-17 18:27:39,859] Trial 13 finished with value: -591.4208786976639 and parameters: {'embedding_dim': 211, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 3 with value: -21.65559039958045.
+[I 2025-12-17 18:28:33,921] Trial 14 finished with value: -505.5147449173316 and parameters: {'embedding_dim': 183, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 3 with value: -21.65559039958045.
+[I 2025-12-17 18:29:12,901] Trial 15 finished with value: -114.17587428122326 and parameters: {'embedding_dim': 224, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 3 with value: -21.65559039958045.
+[I 2025-12-17 18:30:19,806] Trial 16 finished with value: -369.460396173351 and parameters: {'embedding_dim': 182, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 3 with value: -21.65559039958045.
+[I 2025-12-17 18:31:01,733] Trial 17 finished with value: -1397.9266559779344 and parameters: {'embedding_dim': 234, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 3 with value: -21.65559039958045.
+[I 2025-12-17 18:32:20,079] Trial 18 finished with value: -1005.6287226390125 and parameters: {'embedding_dim': 341, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 3 with value: -21.65559039958045.
+[I 2025-12-17 18:32:59,084] Trial 19 finished with value: -188.88936691498992 and parameters: {'embedding_dim': 173, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 3 with value: -21.65559039958045.
+[I 2025-12-17 18:33:56,226] Trial 20 finished with value: -649.1769252250344 and parameters: {'embedding_dim': 133, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 3 with value: -21.65559039958045.
+[I 2025-12-17 18:35:22,454] Trial 21 finished with value: -339.48664647716885 and parameters: {'embedding_dim': 265, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 3 with value: -21.65559039958045.
+[I 2025-12-17 18:36:57,177] Trial 22 finished with value: -80.4570179349952 and parameters: {'embedding_dim': 248, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 3 with value: -21.65559039958045.
+[I 2025-12-17 18:38:26,371] Trial 23 finished with value: -707.0370520090871 and parameters: {'embedding_dim': 197, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 3 with value: -21.65559039958045.
+[I 2025-12-17 18:39:38,768] Trial 24 finished with value: -15.9225331026793 and parameters: {'embedding_dim': 297, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 24 with value: -15.9225331026793.
+[I 2025-12-17 18:40:49,280] Trial 25 finished with value: -1093.0792905827602 and parameters: {'embedding_dim': 325, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 24 with value: -15.9225331026793.
+[I 2025-12-17 18:41:41,714] Trial 26 finished with value: -2192.738471965633 and parameters: {'embedding_dim': 359, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 24 with value: -15.9225331026793.
+[I 2025-12-17 18:42:47,162] Trial 27 finished with value: -371.9049537448667 and parameters: {'embedding_dim': 160, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 24 with value: -15.9225331026793.
+[I 2025-12-17 18:43:22,332] Trial 28 finished with value: -1225.9675419540526 and parameters: {'embedding_dim': 285, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 24 with value: -15.9225331026793.
+[I 2025-12-17 18:43:36,690] Trial 29 finished with value: -601.8666964801505 and parameters: {'embedding_dim': 206, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 24 with value: -15.9225331026793.
+[I 2025-12-17 18:44:43,846] A new study created in memory with name: no-name-f7dd17de-e12a-4a6a-a5ef-24278d172302
+[I 2025-12-17 18:44:50,389] Trial 0 finished with value: -78.4902297764721 and parameters: {'embedding_dim': 124, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -78.4902297764721.
+[I 2025-12-17 18:44:53,626] Trial 1 finished with value: -79.78346185569109 and parameters: {'embedding_dim': 124, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -78.4902297764721.
+[I 2025-12-17 18:45:00,436] Trial 2 finished with value: -187.91797056655767 and parameters: {'embedding_dim': 71, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -78.4902297764721.
+[I 2025-12-17 18:45:03,929] Trial 3 finished with value: -91.31408686207165 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -78.4902297764721.
+[I 2025-12-17 18:45:07,273] Trial 4 finished with value: -38.7009940671079 and parameters: {'embedding_dim': 109, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 4 with value: -38.7009940671079.
+[I 2025-12-17 18:45:10,587] Trial 5 finished with value: -39.93735071912228 and parameters: {'embedding_dim': 113, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 4 with value: -38.7009940671079.
+[I 2025-12-17 18:45:14,284] Trial 6 finished with value: -37.860402129099356 and parameters: {'embedding_dim': 65, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 6 with value: -37.860402129099356.
+[I 2025-12-17 18:45:20,846] Trial 7 finished with value: -49.02516395080848 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 6 with value: -37.860402129099356.
+[I 2025-12-17 18:45:27,334] Trial 8 finished with value: -40.67238654819597 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 6 with value: -37.860402129099356.
+[I 2025-12-17 18:45:32,325] Trial 9 finished with value: -87.92311095412217 and parameters: {'embedding_dim': 71, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 6 with value: -37.860402129099356.
+[I 2025-12-17 18:45:37,662] Trial 10 finished with value: -21.360098163277495 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -21.360098163277495.
+[I 2025-12-17 18:45:42,985] Trial 11 finished with value: -21.296634720444665 and parameters: {'embedding_dim': 65, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -21.296634720444665.
+[I 2025-12-17 18:45:48,323] Trial 12 finished with value: -73.62299160656518 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -21.296634720444665.
+[I 2025-12-17 18:45:53,664] Trial 13 finished with value: -51.85410968500427 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -21.296634720444665.
+[I 2025-12-17 18:45:58,988] Trial 14 finished with value: -14.76799046292875 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -14.76799046292875.
+[I 2025-12-17 18:46:04,357] Trial 15 finished with value: -74.1708538400342 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -14.76799046292875.
+[I 2025-12-17 18:46:09,699] Trial 16 finished with value: -41.25553596600402 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -14.76799046292875.
+[I 2025-12-17 18:46:15,088] Trial 17 finished with value: -41.840030842962435 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -14.76799046292875.
+[I 2025-12-17 18:46:22,316] Trial 18 finished with value: -73.85508647311039 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -14.76799046292875.
+[I 2025-12-17 18:46:27,646] Trial 19 finished with value: -45.36398838879964 and parameters: {'embedding_dim': 97, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -14.76799046292875.
+[I 2025-12-17 18:46:32,970] Trial 20 finished with value: -35.682126468828024 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -14.76799046292875.
+[I 2025-12-17 18:46:38,305] Trial 21 finished with value: -105.2467251795031 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -14.76799046292875.
+[I 2025-12-17 18:46:43,632] Trial 22 finished with value: -173.53058968687031 and parameters: {'embedding_dim': 70, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -14.76799046292875.
+[I 2025-12-17 18:46:48,953] Trial 23 finished with value: -20.07438934875609 and parameters: {'embedding_dim': 79, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -14.76799046292875.
+[I 2025-12-17 18:46:54,307] Trial 24 finished with value: -31.146992165660006 and parameters: {'embedding_dim': 79, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -14.76799046292875.
+[I 2025-12-17 18:46:59,637] Trial 25 finished with value: -14.314004502848233 and parameters: {'embedding_dim': 66, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 25 with value: -14.314004502848233.
+[I 2025-12-17 18:47:03,169] Trial 26 finished with value: -92.209628255603 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 25 with value: -14.314004502848233.
+[I 2025-12-17 18:47:10,471] Trial 27 finished with value: -33.67047732249514 and parameters: {'embedding_dim': 81, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 25 with value: -14.314004502848233.
+[I 2025-12-17 18:47:15,339] Trial 28 finished with value: -32.10408019270135 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 25 with value: -14.314004502848233.
+[I 2025-12-17 18:47:22,106] Trial 29 finished with value: -27.694956819137975 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 25 with value: -14.314004502848233.
+[I 2025-12-17 18:47:26,970] Trial 30 finished with value: -101.31130055980469 and parameters: {'embedding_dim': 67, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 25 with value: -14.314004502848233.
+[I 2025-12-17 18:47:32,314] Trial 31 finished with value: -48.54230269505784 and parameters: {'embedding_dim': 68, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 25 with value: -14.314004502848233.
+[I 2025-12-17 18:47:37,667] Trial 32 finished with value: -1.8982525541949884 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -1.8982525541949884.
+[I 2025-12-17 18:47:43,000] Trial 33 finished with value: -76.63000573689234 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -1.8982525541949884.
+[I 2025-12-17 18:47:48,337] Trial 34 finished with value: -67.09234831235568 and parameters: {'embedding_dim': 128, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -1.8982525541949884.
+[I 2025-12-17 18:47:51,815] Trial 35 finished with value: -51.600271643409755 and parameters: {'embedding_dim': 70, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 32 with value: -1.8982525541949884.
+[I 2025-12-17 18:47:56,836] Trial 36 finished with value: -10.81877801900151 and parameters: {'embedding_dim': 81, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 32 with value: -1.8982525541949884.
+[I 2025-12-17 18:48:00,159] Trial 37 finished with value: -26.885345841034898 and parameters: {'embedding_dim': 74, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 32 with value: -1.8982525541949884.
+[I 2025-12-17 18:48:03,467] Trial 38 finished with value: -64.5874961886723 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 32 with value: -1.8982525541949884.
+[I 2025-12-17 18:48:08,536] Trial 39 finished with value: -7.171092653022217 and parameters: {'embedding_dim': 67, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 32 with value: -1.8982525541949884.
+[I 2025-12-17 18:48:15,324] Trial 40 finished with value: -33.79338676586834 and parameters: {'embedding_dim': 68, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 32 with value: -1.8982525541949884.
+[I 2025-12-17 18:48:20,395] Trial 41 finished with value: -46.910982453125214 and parameters: {'embedding_dim': 65, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 32 with value: -1.8982525541949884.
+[I 2025-12-17 18:48:25,518] Trial 42 finished with value: -224.07890546504547 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 32 with value: -1.8982525541949884.
+[I 2025-12-17 18:48:30,512] Trial 43 finished with value: -66.64894126749893 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 32 with value: -1.8982525541949884.
+[I 2025-12-17 18:48:35,450] Trial 44 finished with value: -28.418600507244424 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 32 with value: -1.8982525541949884.
+[I 2025-12-17 18:48:40,414] Trial 45 finished with value: -74.87410858636738 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 32 with value: -1.8982525541949884.
+[I 2025-12-17 18:48:45,733] Trial 46 finished with value: -28.52147265804105 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 32 with value: -1.8982525541949884.
+[I 2025-12-17 18:48:50,784] Trial 47 finished with value: -61.813983830427134 and parameters: {'embedding_dim': 76, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 32 with value: -1.8982525541949884.
+[I 2025-12-17 18:48:55,807] Trial 48 finished with value: -41.49668008150094 and parameters: {'embedding_dim': 72, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 32 with value: -1.8982525541949884.
+[I 2025-12-17 18:49:02,298] Trial 49 finished with value: -39.2641384223451 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 32 with value: -1.8982525541949884.
+[I 2025-12-17 18:49:07,762] A new study created in memory with name: no-name-1b6f4a93-97d4-43dc-983a-72940cf9d9e0
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_10000_1_incheon_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_10000_1_incheon_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan10000_1_incheon.csv: Class 0=9293 | Class 1=9617
+Saved ../../data/data_oversampled/ctgan10000/ctgan10000_1_incheon.csv: Class 0=9293 | Class 1=9617 | Class 2=14554
+Processing ../../data/data_for_modeling/seoul_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/seoul_train.csv: Optimizing CTGAN for class 1...
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_10000_1_seoul_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_10000_1_seoul_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan10000_1_seoul.csv: Class 0=9402 | Class 1=9927
+Saved ../../data/data_oversampled/ctgan10000/ctgan10000_1_seoul.csv: Class 0=9402 | Class 1=9927 | Class 2=15676
+Processing ../../data/data_for_modeling/busan_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/busan_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-17 18:49:19,699] Trial 0 finished with value: -7370.525410516945 and parameters: {'embedding_dim': 263, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 0 with value: -7370.525410516945.
+[I 2025-12-17 18:49:27,180] Trial 1 finished with value: -275.72518086605163 and parameters: {'embedding_dim': 378, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 1 with value: -275.72518086605163.
+[I 2025-12-17 18:50:02,699] Trial 2 finished with value: -1323.8863691942356 and parameters: {'embedding_dim': 132, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 1 with value: -275.72518086605163.
+[I 2025-12-17 18:50:18,430] Trial 3 finished with value: -405.7385292786847 and parameters: {'embedding_dim': 464, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 1 with value: -275.72518086605163.
+[I 2025-12-17 18:50:29,348] Trial 4 finished with value: -1330.6497490598542 and parameters: {'embedding_dim': 134, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 1 with value: -275.72518086605163.
+[I 2025-12-17 18:50:40,007] Trial 5 finished with value: -510.96667138685837 and parameters: {'embedding_dim': 163, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 1 with value: -275.72518086605163.
+[I 2025-12-17 18:51:09,519] Trial 6 finished with value: -3498.1075143893563 and parameters: {'embedding_dim': 326, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 1 with value: -275.72518086605163.
+[I 2025-12-17 18:51:45,627] Trial 7 finished with value: -1282.896067827549 and parameters: {'embedding_dim': 305, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 1 with value: -275.72518086605163.
+[I 2025-12-17 18:52:01,109] Trial 8 finished with value: -475.1486693977967 and parameters: {'embedding_dim': 319, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 1 with value: -275.72518086605163.
+[I 2025-12-17 18:52:16,855] Trial 9 finished with value: -857.4965857984606 and parameters: {'embedding_dim': 220, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 1 with value: -275.72518086605163.
+[I 2025-12-17 18:52:24,380] Trial 10 finished with value: -1894.2626138886033 and parameters: {'embedding_dim': 437, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 1 with value: -275.72518086605163.
+[I 2025-12-17 18:52:30,543] Trial 11 finished with value: -1355.599176328549 and parameters: {'embedding_dim': 506, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 1 with value: -275.72518086605163.
+[I 2025-12-17 18:52:42,172] Trial 12 finished with value: -455.9669063812342 and parameters: {'embedding_dim': 403, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 1 with value: -275.72518086605163.
+[I 2025-12-17 18:52:53,644] Trial 13 finished with value: -1878.4071722479855 and parameters: {'embedding_dim': 407, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 1 with value: -275.72518086605163.
+[I 2025-12-17 18:53:08,979] Trial 14 finished with value: -1056.8250849834021 and parameters: {'embedding_dim': 501, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 1 with value: -275.72518086605163.
+[I 2025-12-17 18:53:15,684] Trial 15 finished with value: -3608.8427653503672 and parameters: {'embedding_dim': 447, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 1 with value: -275.72518086605163.
+[I 2025-12-17 18:53:26,275] Trial 16 finished with value: -422.47321428813837 and parameters: {'embedding_dim': 380, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 1 with value: -275.72518086605163.
+[I 2025-12-17 18:53:35,322] Trial 17 finished with value: -346.39521049414145 and parameters: {'embedding_dim': 357, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 1 with value: -275.72518086605163.
+[I 2025-12-17 18:53:44,839] Trial 18 finished with value: -178.8663197135195 and parameters: {'embedding_dim': 370, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 18 with value: -178.8663197135195.
+[I 2025-12-17 18:53:51,396] Trial 19 finished with value: -708.7800634595806 and parameters: {'embedding_dim': 270, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 18 with value: -178.8663197135195.
+[I 2025-12-17 18:54:01,348] Trial 20 finished with value: -616.2507395575938 and parameters: {'embedding_dim': 353, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 18 with value: -178.8663197135195.
+[I 2025-12-17 18:54:11,073] Trial 21 finished with value: -258.8323668756531 and parameters: {'embedding_dim': 356, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 18 with value: -178.8663197135195.
+[I 2025-12-17 18:54:17,971] Trial 22 finished with value: -1951.0818302051116 and parameters: {'embedding_dim': 376, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 18 with value: -178.8663197135195.
+[I 2025-12-17 18:54:28,084] Trial 23 finished with value: -483.74565167731214 and parameters: {'embedding_dim': 406, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 18 with value: -178.8663197135195.
+[I 2025-12-17 18:54:38,383] Trial 24 finished with value: -1687.4348467352995 and parameters: {'embedding_dim': 290, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 18 with value: -178.8663197135195.
+[I 2025-12-17 18:54:46,038] Trial 25 finished with value: -1662.1651276742152 and parameters: {'embedding_dim': 349, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 18 with value: -178.8663197135195.
+[I 2025-12-17 18:54:59,217] Trial 26 finished with value: -1374.1038128944388 and parameters: {'embedding_dim': 237, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 18 with value: -178.8663197135195.
+[I 2025-12-17 18:55:16,653] Trial 27 finished with value: -1205.8352463495296 and parameters: {'embedding_dim': 427, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -178.8663197135195.
+[I 2025-12-17 18:55:23,856] Trial 28 finished with value: -4828.943372111573 and parameters: {'embedding_dim': 469, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 18 with value: -178.8663197135195.
+[I 2025-12-17 18:55:36,127] Trial 29 finished with value: -1478.4465379699893 and parameters: {'embedding_dim': 334, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 18 with value: -178.8663197135195.
+[I 2025-12-17 18:55:47,905] A new study created in memory with name: no-name-6a98390c-0665-4c45-acfc-3b0107d9d80f
+[I 2025-12-17 18:55:54,292] Trial 0 finished with value: -121.35977768405475 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -121.35977768405475.
+[I 2025-12-17 18:56:01,348] Trial 1 finished with value: -68.5664945045001 and parameters: {'embedding_dim': 65, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -68.5664945045001.
+[I 2025-12-17 18:56:08,737] Trial 2 finished with value: -98.24547404183002 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -68.5664945045001.
+[I 2025-12-17 18:56:11,967] Trial 3 finished with value: -17.584834904329103 and parameters: {'embedding_dim': 122, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 3 with value: -17.584834904329103.
+[I 2025-12-17 18:56:18,930] Trial 4 finished with value: -97.47828592582843 and parameters: {'embedding_dim': 113, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 3 with value: -17.584834904329103.
+[I 2025-12-17 18:56:21,982] Trial 5 finished with value: -88.81858380879854 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 3 with value: -17.584834904329103.
+[I 2025-12-17 18:56:28,350] Trial 6 finished with value: -35.26798993781809 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 3 with value: -17.584834904329103.
+[I 2025-12-17 18:56:35,428] Trial 7 finished with value: -177.8998200201475 and parameters: {'embedding_dim': 115, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 3 with value: -17.584834904329103.
+[I 2025-12-17 18:56:38,677] Trial 8 finished with value: -179.17940202596645 and parameters: {'embedding_dim': 74, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 3 with value: -17.584834904329103.
+[I 2025-12-17 18:56:43,643] Trial 9 finished with value: -69.43524748058823 and parameters: {'embedding_dim': 109, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 3 with value: -17.584834904329103.
+[I 2025-12-17 18:56:48,555] Trial 10 finished with value: -112.38257350935376 and parameters: {'embedding_dim': 127, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 3 with value: -17.584834904329103.
+[I 2025-12-17 18:56:51,701] Trial 11 finished with value: -312.3164832018398 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 3 with value: -17.584834904329103.
+[I 2025-12-17 18:56:56,458] Trial 12 finished with value: -104.94424284354005 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 3 with value: -17.584834904329103.
+[I 2025-12-17 18:56:59,671] Trial 13 finished with value: -192.4271141430964 and parameters: {'embedding_dim': 88, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 3 with value: -17.584834904329103.
+[I 2025-12-17 18:57:04,433] Trial 14 finished with value: -234.43723580202607 and parameters: {'embedding_dim': 127, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 3 with value: -17.584834904329103.
+[I 2025-12-17 18:57:09,463] Trial 15 finished with value: -274.46722932261565 and parameters: {'embedding_dim': 105, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 3 with value: -17.584834904329103.
+[I 2025-12-17 18:57:12,602] Trial 16 finished with value: -252.31889940083664 and parameters: {'embedding_dim': 120, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 3 with value: -17.584834904329103.
+[I 2025-12-17 18:57:17,554] Trial 17 finished with value: -106.25998419638782 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 3 with value: -17.584834904329103.
+[I 2025-12-17 18:57:22,481] Trial 18 finished with value: -83.76421766040045 and parameters: {'embedding_dim': 104, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 3 with value: -17.584834904329103.
+[I 2025-12-17 18:57:25,614] Trial 19 finished with value: -16.520218167792596 and parameters: {'embedding_dim': 65, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:57:28,743] Trial 20 finished with value: -43.372296156635265 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:57:31,860] Trial 21 finished with value: -253.31261394750578 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:57:34,995] Trial 22 finished with value: -269.31288608002893 and parameters: {'embedding_dim': 71, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:57:38,148] Trial 23 finished with value: -97.56593661266156 and parameters: {'embedding_dim': 80, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:57:42,903] Trial 24 finished with value: -55.084195625232404 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:57:46,117] Trial 25 finished with value: -552.3015206306551 and parameters: {'embedding_dim': 88, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:57:52,503] Trial 26 finished with value: -108.10299383136214 and parameters: {'embedding_dim': 68, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:57:57,262] Trial 27 finished with value: -83.62732092491598 and parameters: {'embedding_dim': 122, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:58:00,629] Trial 28 finished with value: -160.50316256782108 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:58:07,256] Trial 29 finished with value: -33.96201773159294 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:58:13,936] Trial 30 finished with value: -31.5947824277752 and parameters: {'embedding_dim': 94, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:58:20,639] Trial 31 finished with value: -104.58436161886875 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:58:27,283] Trial 32 finished with value: -155.5972409400914 and parameters: {'embedding_dim': 99, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:58:33,955] Trial 33 finished with value: -52.28294403594987 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:58:40,665] Trial 34 finished with value: -144.9121560461917 and parameters: {'embedding_dim': 110, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:58:47,328] Trial 35 finished with value: -177.4468521300475 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:58:54,427] Trial 36 finished with value: -175.65319782497176 and parameters: {'embedding_dim': 117, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:59:01,062] Trial 37 finished with value: -261.56206516312744 and parameters: {'embedding_dim': 109, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:59:07,581] Trial 38 finished with value: -82.68244982385451 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:59:11,155] Trial 39 finished with value: -271.1734312505714 and parameters: {'embedding_dim': 88, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:59:16,064] Trial 40 finished with value: -49.26195349882819 and parameters: {'embedding_dim': 83, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:59:22,474] Trial 41 finished with value: -41.77531739612928 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:59:29,105] Trial 42 finished with value: -167.24250188792632 and parameters: {'embedding_dim': 91, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:59:36,206] Trial 43 finished with value: -39.785999284672634 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:59:42,831] Trial 44 finished with value: -120.36860900622294 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:59:49,217] Trial 45 finished with value: -132.6720269793482 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:59:54,133] Trial 46 finished with value: -320.7001127418713 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 18:59:57,295] Trial 47 finished with value: -159.4866531640818 and parameters: {'embedding_dim': 107, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 19:00:02,290] Trial 48 finished with value: -456.86466832460405 and parameters: {'embedding_dim': 101, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 19:00:08,681] Trial 49 finished with value: -207.29388610310352 and parameters: {'embedding_dim': 113, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 19 with value: -16.520218167792596.
+[I 2025-12-17 19:00:12,055] A new study created in memory with name: no-name-371bafb5-4440-4899-9347-4c37b0a28da4
+[I 2025-12-17 19:00:16,865] Trial 0 finished with value: -4692.557328842285 and parameters: {'embedding_dim': 367, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 0 with value: -4692.557328842285.
+[I 2025-12-17 19:00:27,989] Trial 1 finished with value: -1482.1105859807585 and parameters: {'embedding_dim': 489, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 1 with value: -1482.1105859807585.
+[I 2025-12-17 19:00:36,500] Trial 2 finished with value: -518.1112196740971 and parameters: {'embedding_dim': 219, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 2 with value: -518.1112196740971.
+[I 2025-12-17 19:00:53,105] Trial 3 finished with value: -858.3529294979705 and parameters: {'embedding_dim': 415, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 2 with value: -518.1112196740971.
+[I 2025-12-17 19:01:01,581] Trial 4 finished with value: -590.5008616563533 and parameters: {'embedding_dim': 402, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 2 with value: -518.1112196740971.
+[I 2025-12-17 19:01:12,781] Trial 5 finished with value: -1437.8553241848458 and parameters: {'embedding_dim': 204, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 2 with value: -518.1112196740971.
+[I 2025-12-17 19:01:29,199] Trial 6 finished with value: -1447.2345984617407 and parameters: {'embedding_dim': 369, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -518.1112196740971.
+[I 2025-12-17 19:01:40,129] Trial 7 finished with value: -523.1688944870534 and parameters: {'embedding_dim': 477, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 2 with value: -518.1112196740971.
+[I 2025-12-17 19:01:53,796] Trial 8 finished with value: -950.0706710173117 and parameters: {'embedding_dim': 361, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 2 with value: -518.1112196740971.
+[I 2025-12-17 19:02:05,409] Trial 9 finished with value: -460.1964294971882 and parameters: {'embedding_dim': 414, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 9 with value: -460.1964294971882.
+[I 2025-12-17 19:02:18,861] Trial 10 finished with value: -450.94879352985106 and parameters: {'embedding_dim': 292, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 10 with value: -450.94879352985106.
+[I 2025-12-17 19:02:32,347] Trial 11 finished with value: -1506.382157254884 and parameters: {'embedding_dim': 268, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 10 with value: -450.94879352985106.
+[I 2025-12-17 19:02:43,575] Trial 12 finished with value: -459.3415855724912 and parameters: {'embedding_dim': 138, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 10 with value: -450.94879352985106.
+[I 2025-12-17 19:02:54,821] Trial 13 finished with value: -890.4120440902036 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 10 with value: -450.94879352985106.
+[I 2025-12-17 19:03:08,676] Trial 14 finished with value: -898.8281181076741 and parameters: {'embedding_dim': 133, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 10 with value: -450.94879352985106.
+[I 2025-12-17 19:03:36,365] Trial 15 finished with value: -864.7973377407045 and parameters: {'embedding_dim': 285, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 10 with value: -450.94879352985106.
+[I 2025-12-17 19:03:49,731] Trial 16 finished with value: -438.1470483281794 and parameters: {'embedding_dim': 186, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 16 with value: -438.1470483281794.
+[I 2025-12-17 19:04:03,340] Trial 17 finished with value: -492.99546240092224 and parameters: {'embedding_dim': 202, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 16 with value: -438.1470483281794.
+[I 2025-12-17 19:04:16,821] Trial 18 finished with value: -753.5197357972403 and parameters: {'embedding_dim': 271, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 16 with value: -438.1470483281794.
+[I 2025-12-17 19:04:49,857] Trial 19 finished with value: -918.343518838779 and parameters: {'embedding_dim': 325, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 16 with value: -438.1470483281794.
+[I 2025-12-17 19:04:58,899] Trial 20 finished with value: -695.604446641099 and parameters: {'embedding_dim': 176, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 16 with value: -438.1470483281794.
+[I 2025-12-17 19:05:10,207] Trial 21 finished with value: -652.7413807620833 and parameters: {'embedding_dim': 163, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 16 with value: -438.1470483281794.
+[I 2025-12-17 19:05:21,573] Trial 22 finished with value: -951.6967712651427 and parameters: {'embedding_dim': 234, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 16 with value: -438.1470483281794.
+[I 2025-12-17 19:05:35,206] Trial 23 finished with value: -473.4719580857227 and parameters: {'embedding_dim': 162, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 16 with value: -438.1470483281794.
+[I 2025-12-17 19:05:46,455] Trial 24 finished with value: -647.7880291089349 and parameters: {'embedding_dim': 304, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 16 with value: -438.1470483281794.
+[I 2025-12-17 19:06:00,115] Trial 25 finished with value: -397.9562635256158 and parameters: {'embedding_dim': 248, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 25 with value: -397.9562635256158.
+[I 2025-12-17 19:06:33,454] Trial 26 finished with value: -216.80218991415236 and parameters: {'embedding_dim': 239, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 26 with value: -216.80218991415236.
+[I 2025-12-17 19:07:06,601] Trial 27 finished with value: -261.39433436032425 and parameters: {'embedding_dim': 243, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 26 with value: -216.80218991415236.
+[I 2025-12-17 19:07:44,623] Trial 28 finished with value: -116.72495834568821 and parameters: {'embedding_dim': 240, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 28 with value: -116.72495834568821.
+[I 2025-12-17 19:08:17,484] Trial 29 finished with value: -340.9331994642369 and parameters: {'embedding_dim': 325, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 28 with value: -116.72495834568821.
+[I 2025-12-17 19:08:51,667] A new study created in memory with name: no-name-47ae91bf-448e-4149-b324-a1b26b6979b2
+[I 2025-12-17 19:09:04,414] Trial 0 finished with value: -45.650960169223865 and parameters: {'embedding_dim': 105, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -45.650960169223865.
+[I 2025-12-17 19:09:09,901] Trial 1 finished with value: -120.03011435872529 and parameters: {'embedding_dim': 113, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -45.650960169223865.
+[I 2025-12-17 19:09:15,090] Trial 2 finished with value: -25.145991624002104 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -25.145991624002104.
+[I 2025-12-17 19:09:21,303] Trial 3 finished with value: -126.19995884887066 and parameters: {'embedding_dim': 80, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 2 with value: -25.145991624002104.
+[I 2025-12-17 19:09:34,046] Trial 4 finished with value: -216.03529816758382 and parameters: {'embedding_dim': 102, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -25.145991624002104.
+[I 2025-12-17 19:09:42,257] Trial 5 finished with value: -224.79933948296232 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 2 with value: -25.145991624002104.
+[I 2025-12-17 19:09:47,540] Trial 6 finished with value: -301.5029580402239 and parameters: {'embedding_dim': 66, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -25.145991624002104.
+[I 2025-12-17 19:09:52,400] Trial 7 finished with value: -213.82090105349738 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -25.145991624002104.
+[I 2025-12-17 19:09:56,968] Trial 8 finished with value: -307.11795223274396 and parameters: {'embedding_dim': 125, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -25.145991624002104.
+[I 2025-12-17 19:10:02,153] Trial 9 finished with value: -105.36936836263747 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -25.145991624002104.
+[I 2025-12-17 19:10:09,550] Trial 10 finished with value: -9.399812530591564 and parameters: {'embedding_dim': 88, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:10:16,919] Trial 11 finished with value: -36.796353232399866 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:10:24,293] Trial 12 finished with value: -35.822371137610475 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:10:29,783] Trial 13 finished with value: -52.21683954742658 and parameters: {'embedding_dim': 89, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:10:34,956] Trial 14 finished with value: -20.4644778179386 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:10:45,279] Trial 15 finished with value: -38.6189105546316 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:10:50,484] Trial 16 finished with value: -31.264147588347807 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:10:57,949] Trial 17 finished with value: -108.5546088382095 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:11:06,571] Trial 18 finished with value: -32.44401935300032 and parameters: {'embedding_dim': 68, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:11:11,873] Trial 19 finished with value: -16.64102205400474 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:11:18,690] Trial 20 finished with value: -16.887133344748744 and parameters: {'embedding_dim': 112, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:11:25,605] Trial 21 finished with value: -152.10553044985116 and parameters: {'embedding_dim': 114, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:11:32,500] Trial 22 finished with value: -21.265987346674684 and parameters: {'embedding_dim': 108, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:11:39,421] Trial 23 finished with value: -45.164729950292426 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:11:46,333] Trial 24 finished with value: -72.17271492072656 and parameters: {'embedding_dim': 120, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:11:51,821] Trial 25 finished with value: -60.00587932847298 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:11:58,831] Trial 26 finished with value: -10.692110008480284 and parameters: {'embedding_dim': 91, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:12:03,988] Trial 27 finished with value: -426.68442311295007 and parameters: {'embedding_dim': 91, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:12:18,457] Trial 28 finished with value: -80.0141522001839 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:12:27,124] Trial 29 finished with value: -69.62966794929827 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:12:36,416] Trial 30 finished with value: -30.630240088712156 and parameters: {'embedding_dim': 87, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:12:43,409] Trial 31 finished with value: -150.681381620212 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:12:52,055] Trial 32 finished with value: -150.61319354049976 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:13:00,214] Trial 33 finished with value: -44.86115583755674 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:13:07,148] Trial 34 finished with value: -38.55947002184735 and parameters: {'embedding_dim': 81, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:13:12,347] Trial 35 finished with value: -30.6803035023297 and parameters: {'embedding_dim': 117, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:13:27,465] Trial 36 finished with value: -24.233474683558015 and parameters: {'embedding_dim': 83, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:13:31,993] Trial 37 finished with value: -124.27972971579783 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:13:37,504] Trial 38 finished with value: -166.37204073698084 and parameters: {'embedding_dim': 108, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:13:44,453] Trial 39 finished with value: -20.791841117262713 and parameters: {'embedding_dim': 100, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:13:53,080] Trial 40 finished with value: -175.65224295016074 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:13:58,265] Trial 41 finished with value: -94.78762776097172 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:14:03,468] Trial 42 finished with value: -112.74905274512896 and parameters: {'embedding_dim': 70, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:14:08,681] Trial 43 finished with value: -114.9268206215697 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:14:13,920] Trial 44 finished with value: -18.314652153390227 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:14:20,805] Trial 45 finished with value: -70.52496626669709 and parameters: {'embedding_dim': 88, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:14:26,885] Trial 46 finished with value: -44.968443853214524 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:14:36,035] Trial 47 finished with value: -57.02530469683609 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:14:39,483] Trial 48 finished with value: -86.4390808848199 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 10 with value: -9.399812530591564.
+[I 2025-12-17 19:14:45,035] Trial 49 finished with value: -4.647727881631673 and parameters: {'embedding_dim': 123, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 49 with value: -4.647727881631673.
+[I 2025-12-17 19:14:50,641] A new study created in memory with name: no-name-2a3b2542-352e-4b51-8922-4e388acc3971
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_10000_1_busan_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_10000_1_busan_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan10000_1_busan.csv: Class 0=9572 | Class 1=8855
+Saved ../../data/data_oversampled/ctgan10000/ctgan10000_1_busan.csv: Class 0=9572 | Class 1=8855 | Class 2=16492
+Processing ../../data/data_for_modeling/daegu_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/daegu_train.csv: Optimizing CTGAN for class 1...
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_10000_1_daegu_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_10000_1_daegu_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan10000_1_daegu.csv: Class 0=8787 | Class 1=9506
+Saved ../../data/data_oversampled/ctgan10000/ctgan10000_1_daegu.csv: Class 0=8787 | Class 1=9506 | Class 2=16582
+Processing ../../data/data_for_modeling/daejeon_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/daejeon_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-17 19:16:06,583] Trial 0 finished with value: -45.84995374567559 and parameters: {'embedding_dim': 215, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:16:23,203] Trial 1 finished with value: -1956.924809193025 and parameters: {'embedding_dim': 509, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:16:35,896] Trial 2 finished with value: -261.95058472403673 and parameters: {'embedding_dim': 439, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:16:50,055] Trial 3 finished with value: -376.8996318086928 and parameters: {'embedding_dim': 365, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:17:45,423] Trial 4 finished with value: -833.1956237769599 and parameters: {'embedding_dim': 384, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:18:43,806] Trial 5 finished with value: -307.67981003220905 and parameters: {'embedding_dim': 466, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:18:52,851] Trial 6 finished with value: -5748.576643756939 and parameters: {'embedding_dim': 481, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:19:13,796] Trial 7 finished with value: -384.4198177490798 and parameters: {'embedding_dim': 334, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:19:58,142] Trial 8 finished with value: -1281.3025029089524 and parameters: {'embedding_dim': 169, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:20:19,943] Trial 9 finished with value: -533.7899532723652 and parameters: {'embedding_dim': 204, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:21:42,192] Trial 10 finished with value: -476.4706348785866 and parameters: {'embedding_dim': 248, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:22:27,077] Trial 11 finished with value: -423.17938977283825 and parameters: {'embedding_dim': 265, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:22:46,888] Trial 12 finished with value: -159.2288782056262 and parameters: {'embedding_dim': 136, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:23:04,957] Trial 13 finished with value: -221.1722283026166 and parameters: {'embedding_dim': 137, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:24:22,667] Trial 14 finished with value: -1436.6350550720326 and parameters: {'embedding_dim': 225, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:24:42,605] Trial 15 finished with value: -301.7471660926917 and parameters: {'embedding_dim': 139, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:26:04,322] Trial 16 finished with value: -250.13173196558725 and parameters: {'embedding_dim': 297, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:26:25,676] Trial 17 finished with value: -692.3479288755119 and parameters: {'embedding_dim': 187, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:27:45,539] Trial 18 finished with value: -479.5452650996404 and parameters: {'embedding_dim': 176, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:28:20,211] Trial 19 finished with value: -53.56467477742262 and parameters: {'embedding_dim': 285, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:28:48,887] Trial 20 finished with value: -483.2389744173175 and parameters: {'embedding_dim': 277, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:29:24,060] Trial 21 finished with value: -493.6418309793746 and parameters: {'embedding_dim': 229, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:29:58,698] Trial 22 finished with value: -646.2501635010492 and parameters: {'embedding_dim': 315, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:30:27,563] Trial 23 finished with value: -237.33509496510868 and parameters: {'embedding_dim': 158, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:30:48,250] Trial 24 finished with value: -350.99840545653365 and parameters: {'embedding_dim': 205, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:31:22,669] Trial 25 finished with value: -233.90530360090813 and parameters: {'embedding_dim': 128, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:32:15,630] Trial 26 finished with value: -62.76219387963834 and parameters: {'embedding_dim': 235, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:33:08,072] Trial 27 finished with value: -1896.9141112256918 and parameters: {'embedding_dim': 288, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -45.84995374567559.
+[I 2025-12-17 19:33:47,748] Trial 28 finished with value: -25.681403111083156 and parameters: {'embedding_dim': 343, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 28 with value: -25.681403111083156.
+[I 2025-12-17 19:34:14,316] Trial 29 finished with value: -3055.7056132420685 and parameters: {'embedding_dim': 399, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 28 with value: -25.681403111083156.
+[I 2025-12-17 19:34:54,106] A new study created in memory with name: no-name-ea21e6ff-b809-4a94-bbeb-8f3548862df9
+[I 2025-12-17 19:35:00,878] Trial 0 finished with value: -129.37197252176287 and parameters: {'embedding_dim': 122, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -129.37197252176287.
+[I 2025-12-17 19:35:07,356] Trial 1 finished with value: -104.42261008699191 and parameters: {'embedding_dim': 79, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 1 with value: -104.42261008699191.
+[I 2025-12-17 19:35:14,117] Trial 2 finished with value: -29.735232615952167 and parameters: {'embedding_dim': 117, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -29.735232615952167.
+[I 2025-12-17 19:35:20,662] Trial 3 finished with value: -152.5675388577862 and parameters: {'embedding_dim': 125, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -29.735232615952167.
+[I 2025-12-17 19:35:24,132] Trial 4 finished with value: -66.49529741753642 and parameters: {'embedding_dim': 87, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -29.735232615952167.
+[I 2025-12-17 19:35:30,918] Trial 5 finished with value: -150.4287617573088 and parameters: {'embedding_dim': 65, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -29.735232615952167.
+[I 2025-12-17 19:35:35,955] Trial 6 finished with value: -153.70752806315008 and parameters: {'embedding_dim': 124, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -29.735232615952167.
+[I 2025-12-17 19:35:39,358] Trial 7 finished with value: -136.99840974207365 and parameters: {'embedding_dim': 109, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -29.735232615952167.
+[I 2025-12-17 19:35:45,864] Trial 8 finished with value: -63.33105089673761 and parameters: {'embedding_dim': 71, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -29.735232615952167.
+[I 2025-12-17 19:35:49,165] Trial 9 finished with value: -38.86255259352047 and parameters: {'embedding_dim': 123, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -29.735232615952167.
+[I 2025-12-17 19:35:54,504] Trial 10 finished with value: -2.3795075181200165 and parameters: {'embedding_dim': 103, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:35:59,846] Trial 11 finished with value: -32.53724390503852 and parameters: {'embedding_dim': 103, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:36:05,172] Trial 12 finished with value: -97.00837315916768 and parameters: {'embedding_dim': 110, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:36:10,538] Trial 13 finished with value: -98.68661903402905 and parameters: {'embedding_dim': 95, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:36:15,903] Trial 14 finished with value: -33.518475835687674 and parameters: {'embedding_dim': 113, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:36:20,974] Trial 15 finished with value: -34.74261559355247 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:36:28,257] Trial 16 finished with value: -3.056836718796432 and parameters: {'embedding_dim': 116, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:36:31,725] Trial 17 finished with value: -195.11758953417834 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:36:37,112] Trial 18 finished with value: -209.85492985869055 and parameters: {'embedding_dim': 91, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:36:44,424] Trial 19 finished with value: -100.89419636928757 and parameters: {'embedding_dim': 106, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:36:49,840] Trial 20 finished with value: -35.59778383786883 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:36:57,138] Trial 21 finished with value: -115.32187957714595 and parameters: {'embedding_dim': 115, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:37:03,978] Trial 22 finished with value: -34.302918735075174 and parameters: {'embedding_dim': 118, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:37:10,556] Trial 23 finished with value: -181.99334627320212 and parameters: {'embedding_dim': 117, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:37:15,953] Trial 24 finished with value: -159.2415715607013 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:37:22,725] Trial 25 finished with value: -8.244717606857494 and parameters: {'embedding_dim': 105, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:37:29,970] Trial 26 finished with value: -60.45346427278479 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:37:35,330] Trial 27 finished with value: -115.49415269258348 and parameters: {'embedding_dim': 109, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:37:41,974] Trial 28 finished with value: -38.402601946217594 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:37:48,770] Trial 29 finished with value: -31.175216898663656 and parameters: {'embedding_dim': 91, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:37:53,813] Trial 30 finished with value: -47.76085598363006 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:38:00,583] Trial 31 finished with value: -28.678947423714426 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:38:07,342] Trial 32 finished with value: -14.863513743388097 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:38:14,183] Trial 33 finished with value: -247.9100942022685 and parameters: {'embedding_dim': 107, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:38:21,003] Trial 34 finished with value: -117.38008178324422 and parameters: {'embedding_dim': 121, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:38:27,787] Trial 35 finished with value: -63.550862771553795 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:38:34,370] Trial 36 finished with value: -99.07542111541966 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:38:41,241] Trial 37 finished with value: -26.606312984199633 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:38:48,453] Trial 38 finished with value: -91.05339995529373 and parameters: {'embedding_dim': 127, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:38:51,805] Trial 39 finished with value: -22.45371309952503 and parameters: {'embedding_dim': 121, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:38:56,734] Trial 40 finished with value: -76.59308981638338 and parameters: {'embedding_dim': 112, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:39:00,247] Trial 41 finished with value: -52.465291469693824 and parameters: {'embedding_dim': 121, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:39:03,577] Trial 42 finished with value: -254.60701941707723 and parameters: {'embedding_dim': 123, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:39:06,924] Trial 43 finished with value: -20.970031474092686 and parameters: {'embedding_dim': 116, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:39:10,275] Trial 44 finished with value: -419.7615616141689 and parameters: {'embedding_dim': 116, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:39:17,043] Trial 45 finished with value: -71.29765521722499 and parameters: {'embedding_dim': 108, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:39:20,689] Trial 46 finished with value: -44.497963304126344 and parameters: {'embedding_dim': 125, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:39:28,052] Trial 47 finished with value: -167.90394160164865 and parameters: {'embedding_dim': 96, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:39:33,093] Trial 48 finished with value: -26.076626344871602 and parameters: {'embedding_dim': 73, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:39:40,300] Trial 49 finished with value: -16.044438247891165 and parameters: {'embedding_dim': 113, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 10 with value: -2.3795075181200165.
+[I 2025-12-17 19:39:45,801] A new study created in memory with name: no-name-6224ee47-2cd9-4bd9-8c88-4822fe395b9c
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_10000_1_daejeon_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_10000_1_daejeon_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan10000_1_daejeon.csv: Class 0=7951 | Class 1=9879
+Saved ../../data/data_oversampled/ctgan10000/ctgan10000_1_daejeon.csv: Class 0=7951 | Class 1=9879 | Class 2=15441
+Processing ../../data/data_for_modeling/gwangju_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/gwangju_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-17 19:40:06,252] Trial 0 finished with value: -578.570636369471 and parameters: {'embedding_dim': 417, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 0 with value: -578.570636369471.
+[I 2025-12-17 19:40:56,512] Trial 1 finished with value: -1118.2921008676394 and parameters: {'embedding_dim': 322, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -578.570636369471.
+[I 2025-12-17 19:41:41,838] Trial 2 finished with value: -630.4394118767987 and parameters: {'embedding_dim': 501, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 0 with value: -578.570636369471.
+[I 2025-12-17 19:42:01,044] Trial 3 finished with value: -947.4885499126938 and parameters: {'embedding_dim': 376, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 0 with value: -578.570636369471.
+[I 2025-12-17 19:42:20,853] Trial 4 finished with value: -533.2632938147892 and parameters: {'embedding_dim': 475, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 4 with value: -533.2632938147892.
+[I 2025-12-17 19:42:49,256] Trial 5 finished with value: -518.0198575181287 and parameters: {'embedding_dim': 370, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 5 with value: -518.0198575181287.
+[I 2025-12-17 19:42:59,911] Trial 6 finished with value: -744.3924488585371 and parameters: {'embedding_dim': 222, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 5 with value: -518.0198575181287.
+[I 2025-12-17 19:43:08,149] Trial 7 finished with value: -807.4028591677862 and parameters: {'embedding_dim': 508, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 5 with value: -518.0198575181287.
+[I 2025-12-17 19:43:20,312] Trial 8 finished with value: -3178.1198133798416 and parameters: {'embedding_dim': 197, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 5 with value: -518.0198575181287.
+[I 2025-12-17 19:43:45,107] Trial 9 finished with value: -2337.8284907880034 and parameters: {'embedding_dim': 359, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 5 with value: -518.0198575181287.
+[I 2025-12-17 19:44:12,987] Trial 10 finished with value: -106.8575090290698 and parameters: {'embedding_dim': 265, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 10 with value: -106.8575090290698.
+[I 2025-12-17 19:44:43,328] Trial 11 finished with value: -206.61638791818098 and parameters: {'embedding_dim': 262, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 10 with value: -106.8575090290698.
+[I 2025-12-17 19:45:19,364] Trial 12 finished with value: -235.35610223661115 and parameters: {'embedding_dim': 253, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 10 with value: -106.8575090290698.
+[I 2025-12-17 19:45:50,412] Trial 13 finished with value: -506.15563849485716 and parameters: {'embedding_dim': 142, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 10 with value: -106.8575090290698.
+[I 2025-12-17 19:46:28,890] Trial 14 finished with value: -332.23285367377576 and parameters: {'embedding_dim': 275, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -106.8575090290698.
+[I 2025-12-17 19:46:43,949] Trial 15 finished with value: -1945.5001878615487 and parameters: {'embedding_dim': 292, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 10 with value: -106.8575090290698.
+[I 2025-12-17 19:47:18,617] Trial 16 finished with value: -141.62603298090448 and parameters: {'embedding_dim': 180, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 10 with value: -106.8575090290698.
+[I 2025-12-17 19:48:21,613] Trial 17 finished with value: -822.5180322549202 and parameters: {'embedding_dim': 130, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 10 with value: -106.8575090290698.
+[I 2025-12-17 19:49:03,035] Trial 18 finished with value: -139.2619349144477 and parameters: {'embedding_dim': 208, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 10 with value: -106.8575090290698.
+[I 2025-12-17 19:49:46,562] Trial 19 finished with value: -141.53830514989536 and parameters: {'embedding_dim': 210, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 10 with value: -106.8575090290698.
+[I 2025-12-17 19:50:28,896] Trial 20 finished with value: -682.2011196006601 and parameters: {'embedding_dim': 323, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 10 with value: -106.8575090290698.
+[I 2025-12-17 19:51:10,365] Trial 21 finished with value: -253.26426949198083 and parameters: {'embedding_dim': 224, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 10 with value: -106.8575090290698.
+[I 2025-12-17 19:51:53,890] Trial 22 finished with value: -206.22015089400023 and parameters: {'embedding_dim': 179, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 10 with value: -106.8575090290698.
+[I 2025-12-17 19:52:28,133] Trial 23 finished with value: -440.4672023762768 and parameters: {'embedding_dim': 222, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 10 with value: -106.8575090290698.
+[I 2025-12-17 19:53:11,322] Trial 24 finished with value: -115.1205849068594 and parameters: {'embedding_dim': 167, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 10 with value: -106.8575090290698.
+[I 2025-12-17 19:54:10,317] Trial 25 finished with value: -140.31792985412503 and parameters: {'embedding_dim': 162, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 10 with value: -106.8575090290698.
+[I 2025-12-17 19:54:40,119] Trial 26 finished with value: -1632.9662666894858 and parameters: {'embedding_dim': 242, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 10 with value: -106.8575090290698.
+[I 2025-12-17 19:55:22,864] Trial 27 finished with value: -383.72009456506964 and parameters: {'embedding_dim': 297, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 10 with value: -106.8575090290698.
+[I 2025-12-17 19:55:52,261] Trial 28 finished with value: -377.9819018837941 and parameters: {'embedding_dim': 179, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 10 with value: -106.8575090290698.
+[I 2025-12-17 19:56:50,636] Trial 29 finished with value: -352.5984071403577 and parameters: {'embedding_dim': 155, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 10 with value: -106.8575090290698.
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_10000_1_gwangju_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_10000_1_gwangju_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan10000_1_gwangju.csv: Class 0=9015 | Class 1=9456
+Saved ../../data/data_oversampled/ctgan10000/ctgan10000_1_gwangju.csv: Class 0=9015 | Class 1=9456 | Class 2=15692
+
+Running ctgan_sample_10000_2.py...
+[I 2025-12-17 19:57:22,485] A new study created in memory with name: no-name-1032ea77-4366-44b3-9775-e77fb6c237f9
+[I 2025-12-17 19:57:30,965] Trial 0 finished with value: -50.84948183130197 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -50.84948183130197.
+[I 2025-12-17 19:57:45,793] Trial 1 finished with value: -20.948591811503704 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 1 with value: -20.948591811503704.
+[I 2025-12-17 19:57:55,760] Trial 2 finished with value: -80.72105124734627 and parameters: {'embedding_dim': 118, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -20.948591811503704.
+[I 2025-12-17 19:58:11,029] Trial 3 finished with value: -9.714445983783698 and parameters: {'embedding_dim': 100, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 3 with value: -9.714445983783698.
+[I 2025-12-17 19:58:25,570] Trial 4 finished with value: -21.083401387768454 and parameters: {'embedding_dim': 79, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 3 with value: -9.714445983783698.
+[I 2025-12-17 19:58:35,693] Trial 5 finished with value: -238.71684027342988 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 3 with value: -9.714445983783698.
+[I 2025-12-17 19:58:49,231] Trial 6 finished with value: -14.24203264874851 and parameters: {'embedding_dim': 117, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 3 with value: -9.714445983783698.
+[I 2025-12-17 19:59:12,372] Trial 7 finished with value: -104.86754467933248 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 3 with value: -9.714445983783698.
+[I 2025-12-17 19:59:20,629] Trial 8 finished with value: -106.52783967068348 and parameters: {'embedding_dim': 66, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 3 with value: -9.714445983783698.
+[I 2025-12-17 19:59:32,017] Trial 9 finished with value: -15.424000902753635 and parameters: {'embedding_dim': 91, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 3 with value: -9.714445983783698.
+[I 2025-12-17 19:59:45,490] Trial 10 finished with value: -5.043513573656929 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 10 with value: -5.043513573656929.
+[I 2025-12-17 19:59:58,923] Trial 11 finished with value: -4.280785697633835 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 11 with value: -4.280785697633835.
+[I 2025-12-17 20:00:12,421] Trial 12 finished with value: -93.2649336644752 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 11 with value: -4.280785697633835.
+[I 2025-12-17 20:00:27,877] Trial 13 finished with value: -14.262046563094462 and parameters: {'embedding_dim': 108, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 11 with value: -4.280785697633835.
+[I 2025-12-17 20:00:35,541] Trial 14 finished with value: -30.002819842277557 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 11 with value: -4.280785697633835.
+[I 2025-12-17 20:00:45,587] Trial 15 finished with value: -71.66644931654461 and parameters: {'embedding_dim': 110, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 11 with value: -4.280785697633835.
+[I 2025-12-17 20:00:59,099] Trial 16 finished with value: -7.6884863314954375 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 11 with value: -4.280785697633835.
+[I 2025-12-17 20:01:05,645] Trial 17 finished with value: -24.969817002474194 and parameters: {'embedding_dim': 108, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 11 with value: -4.280785697633835.
+[I 2025-12-17 20:01:36,974] Trial 18 finished with value: -33.86094623915246 and parameters: {'embedding_dim': 125, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 11 with value: -4.280785697633835.
+[I 2025-12-17 20:01:44,238] Trial 19 finished with value: -87.02156222772521 and parameters: {'embedding_dim': 99, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -4.280785697633835.
+[I 2025-12-17 20:01:54,332] Trial 20 finished with value: -4.95770949611519 and parameters: {'embedding_dim': 83, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 11 with value: -4.280785697633835.
+[I 2025-12-17 20:02:04,263] Trial 21 finished with value: -130.70281428026087 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 11 with value: -4.280785697633835.
+[I 2025-12-17 20:02:14,182] Trial 22 finished with value: -233.47861071682215 and parameters: {'embedding_dim': 83, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 11 with value: -4.280785697633835.
+[I 2025-12-17 20:02:28,811] Trial 23 finished with value: -116.2051831557996 and parameters: {'embedding_dim': 104, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 11 with value: -4.280785697633835.
+[I 2025-12-17 20:02:36,245] Trial 24 finished with value: -85.56624776987316 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 11 with value: -4.280785697633835.
+[I 2025-12-17 20:02:46,130] Trial 25 finished with value: -128.21895457011314 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 11 with value: -4.280785697633835.
+[I 2025-12-17 20:02:59,626] Trial 26 finished with value: -36.82025086218876 and parameters: {'embedding_dim': 72, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 11 with value: -4.280785697633835.
+[I 2025-12-17 20:03:09,684] Trial 27 finished with value: -28.098127894514654 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 11 with value: -4.280785697633835.
+[I 2025-12-17 20:03:43,275] Trial 28 finished with value: -173.18689734829093 and parameters: {'embedding_dim': 87, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 11 with value: -4.280785697633835.
+[I 2025-12-17 20:03:50,980] Trial 29 finished with value: -18.950743201863926 and parameters: {'embedding_dim': 114, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 11 with value: -4.280785697633835.
+[I 2025-12-17 20:03:56,787] Trial 30 finished with value: -26.002378379814065 and parameters: {'embedding_dim': 105, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -4.280785697633835.
+[I 2025-12-17 20:04:10,339] Trial 31 finished with value: -22.281438315538896 and parameters: {'embedding_dim': 94, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 11 with value: -4.280785697633835.
+[I 2025-12-17 20:04:23,849] Trial 32 finished with value: -113.69080244523751 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 11 with value: -4.280785697633835.
+[I 2025-12-17 20:04:37,346] Trial 33 finished with value: -0.7183962526633656 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 33 with value: -0.7183962526633656.
+[I 2025-12-17 20:04:53,042] Trial 34 finished with value: -23.913471060237814 and parameters: {'embedding_dim': 73, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 33 with value: -0.7183962526633656.
+[I 2025-12-17 20:05:08,146] Trial 35 finished with value: -54.4233414690326 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 33 with value: -0.7183962526633656.
+[I 2025-12-17 20:05:31,064] Trial 36 finished with value: -202.20127443666811 and parameters: {'embedding_dim': 65, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 33 with value: -0.7183962526633656.
+[I 2025-12-17 20:05:37,720] Trial 37 finished with value: -150.07166544472213 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 33 with value: -0.7183962526633656.
+[I 2025-12-17 20:05:51,190] Trial 38 finished with value: -59.37448735518463 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 33 with value: -0.7183962526633656.
+[I 2025-12-17 20:06:02,895] Trial 39 finished with value: -121.41309988179125 and parameters: {'embedding_dim': 68, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 33 with value: -0.7183962526633656.
+[I 2025-12-17 20:06:33,916] Trial 40 finished with value: -0.2656926524769329 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 40 with value: -0.2656926524769329.
+[I 2025-12-17 20:07:05,100] Trial 41 finished with value: -44.298512007687115 and parameters: {'embedding_dim': 81, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 40 with value: -0.2656926524769329.
+[I 2025-12-17 20:07:36,154] Trial 42 finished with value: -44.08740534007484 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 40 with value: -0.2656926524769329.
+[I 2025-12-17 20:08:07,432] Trial 43 finished with value: -114.15158339061733 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 40 with value: -0.2656926524769329.
+[I 2025-12-17 20:08:38,626] Trial 44 finished with value: -42.58452272099496 and parameters: {'embedding_dim': 69, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 40 with value: -0.2656926524769329.
+[I 2025-12-17 20:09:09,746] Trial 45 finished with value: -120.2102187080338 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 40 with value: -0.2656926524769329.
+[I 2025-12-17 20:09:23,508] Trial 46 finished with value: -87.95430073001155 and parameters: {'embedding_dim': 70, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 40 with value: -0.2656926524769329.
+[I 2025-12-17 20:09:29,285] Trial 47 finished with value: -4.323344347147661 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 40 with value: -0.2656926524769329.
+[I 2025-12-17 20:09:35,091] Trial 48 finished with value: -10.420622560061517 and parameters: {'embedding_dim': 114, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 40 with value: -0.2656926524769329.
+[I 2025-12-17 20:09:40,884] Trial 49 finished with value: -41.86959546734201 and parameters: {'embedding_dim': 87, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 40 with value: -0.2656926524769329.
+[I 2025-12-17 20:10:12,582] A new study created in memory with name: no-name-9d82b59d-96a2-4f53-b100-103c288e9095
+Using device: cuda
+Processing ../../data/data_for_modeling/incheon_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/incheon_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-17 20:10:34,346] Trial 0 finished with value: -1092.768723070435 and parameters: {'embedding_dim': 189, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 0 with value: -1092.768723070435.
+[I 2025-12-17 20:11:26,006] Trial 1 finished with value: -194.0805031355266 and parameters: {'embedding_dim': 436, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -194.0805031355266.
+[I 2025-12-17 20:11:58,583] Trial 2 finished with value: -142.5208369798003 and parameters: {'embedding_dim': 498, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -142.5208369798003.
+[I 2025-12-17 20:12:17,946] Trial 3 finished with value: -288.08732102635224 and parameters: {'embedding_dim': 285, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 2 with value: -142.5208369798003.
+[I 2025-12-17 20:12:50,088] Trial 4 finished with value: -66.73040885579978 and parameters: {'embedding_dim': 369, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 4 with value: -66.73040885579978.
+[I 2025-12-17 20:13:27,991] Trial 5 finished with value: -328.56033865598204 and parameters: {'embedding_dim': 205, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 4 with value: -66.73040885579978.
+[I 2025-12-17 20:14:36,208] Trial 6 finished with value: -984.9896331384256 and parameters: {'embedding_dim': 405, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -66.73040885579978.
+[I 2025-12-17 20:14:49,805] Trial 7 finished with value: -2024.1760243489011 and parameters: {'embedding_dim': 148, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 4 with value: -66.73040885579978.
+[I 2025-12-17 20:15:26,424] Trial 8 finished with value: -565.6043830831361 and parameters: {'embedding_dim': 367, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 4 with value: -66.73040885579978.
+[I 2025-12-17 20:16:33,063] Trial 9 finished with value: -218.2192074881689 and parameters: {'embedding_dim': 133, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -66.73040885579978.
+[I 2025-12-17 20:17:18,471] Trial 10 finished with value: -420.46546919373446 and parameters: {'embedding_dim': 288, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 4 with value: -66.73040885579978.
+[I 2025-12-17 20:18:05,444] Trial 11 finished with value: -650.9554341905655 and parameters: {'embedding_dim': 507, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 4 with value: -66.73040885579978.
+[I 2025-12-17 20:18:38,322] Trial 12 finished with value: -808.5413438170625 and parameters: {'embedding_dim': 510, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 4 with value: -66.73040885579978.
+[I 2025-12-17 20:20:02,386] Trial 13 finished with value: -175.38915499519223 and parameters: {'embedding_dim': 436, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 4 with value: -66.73040885579978.
+[I 2025-12-17 20:20:49,041] Trial 14 finished with value: -60.3259649942897 and parameters: {'embedding_dim': 358, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 14 with value: -60.3259649942897.
+[I 2025-12-17 20:21:35,258] Trial 15 finished with value: -94.22051407725606 and parameters: {'embedding_dim': 346, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 14 with value: -60.3259649942897.
+[I 2025-12-17 20:22:33,085] Trial 16 finished with value: -526.7190806090422 and parameters: {'embedding_dim': 301, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 14 with value: -60.3259649942897.
+[I 2025-12-17 20:23:16,472] Trial 17 finished with value: -353.8720746120001 and parameters: {'embedding_dim': 248, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 14 with value: -60.3259649942897.
+[I 2025-12-17 20:24:06,335] Trial 18 finished with value: -181.63671558466382 and parameters: {'embedding_dim': 367, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 14 with value: -60.3259649942897.
+[I 2025-12-17 20:24:44,225] Trial 19 finished with value: -420.2204024613178 and parameters: {'embedding_dim': 399, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 14 with value: -60.3259649942897.
+[I 2025-12-17 20:25:09,989] Trial 20 finished with value: -204.0364828119416 and parameters: {'embedding_dim': 333, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 14 with value: -60.3259649942897.
+[I 2025-12-17 20:25:57,942] Trial 21 finished with value: -376.85196298121963 and parameters: {'embedding_dim': 357, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 14 with value: -60.3259649942897.
+[I 2025-12-17 20:26:44,111] Trial 22 finished with value: -25.05615157241079 and parameters: {'embedding_dim': 325, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 22 with value: -25.05615157241079.
+[I 2025-12-17 20:27:32,637] Trial 23 finished with value: -736.6056591112231 and parameters: {'embedding_dim': 254, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 22 with value: -25.05615157241079.
+[I 2025-12-17 20:28:10,612] Trial 24 finished with value: -667.8205933020888 and parameters: {'embedding_dim': 404, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 22 with value: -25.05615157241079.
+[I 2025-12-17 20:29:09,444] Trial 25 finished with value: -15.698458642708497 and parameters: {'embedding_dim': 311, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 25 with value: -15.698458642708497.
+[I 2025-12-17 20:30:05,976] Trial 26 finished with value: -88.90154516033334 and parameters: {'embedding_dim': 311, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 25 with value: -15.698458642708497.
+[I 2025-12-17 20:31:03,453] Trial 27 finished with value: -268.8261481996696 and parameters: {'embedding_dim': 232, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 25 with value: -15.698458642708497.
+[I 2025-12-17 20:32:00,629] Trial 28 finished with value: -437.6710572950491 and parameters: {'embedding_dim': 274, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 25 with value: -15.698458642708497.
+[I 2025-12-17 20:32:47,563] Trial 29 finished with value: -469.6329630262559 and parameters: {'embedding_dim': 322, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 25 with value: -15.698458642708497.
+[I 2025-12-17 20:33:48,821] A new study created in memory with name: no-name-b85d7509-5752-4221-9dcb-32c4e3f7bd9a
+[I 2025-12-17 20:33:53,698] Trial 0 finished with value: -51.160821498995475 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -51.160821498995475.
+[I 2025-12-17 20:34:00,916] Trial 1 finished with value: -23.624560378752292 and parameters: {'embedding_dim': 112, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -23.624560378752292.
+[I 2025-12-17 20:34:06,277] Trial 2 finished with value: -4.276731969938876 and parameters: {'embedding_dim': 105, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -4.276731969938876.
+[I 2025-12-17 20:34:13,028] Trial 3 finished with value: -52.53973231128766 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -4.276731969938876.
+[I 2025-12-17 20:34:20,564] Trial 4 finished with value: -2.1522266515169184 and parameters: {'embedding_dim': 98, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:34:23,874] Trial 5 finished with value: -373.8847895566226 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:34:30,647] Trial 6 finished with value: -53.10221003606449 and parameters: {'embedding_dim': 91, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:34:34,042] Trial 7 finished with value: -192.2412951055116 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:34:38,895] Trial 8 finished with value: -108.39603286401812 and parameters: {'embedding_dim': 118, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:34:42,072] Trial 9 finished with value: -31.292881799632376 and parameters: {'embedding_dim': 113, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:34:48,554] Trial 10 finished with value: -41.93840551784044 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:34:53,877] Trial 11 finished with value: -83.03467034266151 and parameters: {'embedding_dim': 126, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:34:59,642] Trial 12 finished with value: -102.74933543020074 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:35:07,217] Trial 13 finished with value: -51.11243722567663 and parameters: {'embedding_dim': 83, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:35:14,417] Trial 14 finished with value: -15.623469771168768 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:35:19,251] Trial 15 finished with value: -12.620439836215775 and parameters: {'embedding_dim': 88, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:35:26,483] Trial 16 finished with value: -8.64662727786039 and parameters: {'embedding_dim': 110, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:35:29,700] Trial 17 finished with value: -3.903840079045669 and parameters: {'embedding_dim': 123, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:35:32,951] Trial 18 finished with value: -97.87827540622733 and parameters: {'embedding_dim': 125, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:35:37,770] Trial 19 finished with value: -147.3185705509817 and parameters: {'embedding_dim': 117, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:35:41,027] Trial 20 finished with value: -23.565021372534545 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:35:45,887] Trial 21 finished with value: -28.20124412756827 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:35:52,490] Trial 22 finished with value: -122.84887570722813 and parameters: {'embedding_dim': 107, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:35:55,937] Trial 23 finished with value: -8.5392280180623 and parameters: {'embedding_dim': 120, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:36:01,785] Trial 24 finished with value: -4.099738687921926 and parameters: {'embedding_dim': 96, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:36:07,589] Trial 25 finished with value: -33.20211708700722 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:36:14,079] Trial 26 finished with value: -40.1150407981651 and parameters: {'embedding_dim': 84, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:36:17,292] Trial 27 finished with value: -165.9194567239467 and parameters: {'embedding_dim': 76, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:36:22,166] Trial 28 finished with value: -25.0260146222446 and parameters: {'embedding_dim': 88, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:36:27,020] Trial 29 finished with value: -103.97521991868895 and parameters: {'embedding_dim': 96, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:36:33,497] Trial 30 finished with value: -78.32107080937195 and parameters: {'embedding_dim': 101, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:36:38,798] Trial 31 finished with value: -118.16681144991702 and parameters: {'embedding_dim': 106, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:36:44,755] Trial 32 finished with value: -47.00842693127063 and parameters: {'embedding_dim': 109, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:36:50,143] Trial 33 finished with value: -106.81702078389235 and parameters: {'embedding_dim': 113, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:36:53,478] Trial 34 finished with value: -140.92026195240186 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:37:00,258] Trial 35 finished with value: -81.05772871787218 and parameters: {'embedding_dim': 122, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:37:05,137] Trial 36 finished with value: -353.9585994545302 and parameters: {'embedding_dim': 66, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:37:10,146] Trial 37 finished with value: -27.88748706803295 and parameters: {'embedding_dim': 91, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:37:13,645] Trial 38 finished with value: -113.3930310002026 and parameters: {'embedding_dim': 116, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:37:21,692] Trial 39 finished with value: -121.19676084412036 and parameters: {'embedding_dim': 99, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:37:26,621] Trial 40 finished with value: -196.676176402004 and parameters: {'embedding_dim': 94, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:37:30,175] Trial 41 finished with value: -64.46589178312999 and parameters: {'embedding_dim': 120, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:37:33,643] Trial 42 finished with value: -49.37140710783328 and parameters: {'embedding_dim': 115, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:37:37,197] Trial 43 finished with value: -82.89982111491099 and parameters: {'embedding_dim': 122, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:37:42,933] Trial 44 finished with value: -75.01894879074557 and parameters: {'embedding_dim': 123, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:37:46,430] Trial 45 finished with value: -44.55107739809211 and parameters: {'embedding_dim': 104, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:37:51,434] Trial 46 finished with value: -47.555871452771626 and parameters: {'embedding_dim': 119, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:37:55,524] Trial 47 finished with value: -22.322203024562295 and parameters: {'embedding_dim': 109, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:38:04,936] Trial 48 finished with value: -25.711151233065067 and parameters: {'embedding_dim': 88, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:38:09,788] Trial 49 finished with value: -21.37824118545819 and parameters: {'embedding_dim': 112, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 4 with value: -2.1522266515169184.
+[I 2025-12-17 20:38:16,517] A new study created in memory with name: no-name-0cb25b6f-94a6-4714-b798-a4616c79afd4
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_10000_2_incheon_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_10000_2_incheon_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan10000_2_incheon.csv: Class 0=9583 | Class 1=9739
+Saved ../../data/data_oversampled/ctgan10000/ctgan10000_2_incheon.csv: Class 0=9583 | Class 1=9739 | Class 2=14637
+Processing ../../data/data_for_modeling/seoul_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/seoul_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-17 20:38:41,114] Trial 0 finished with value: -571.897944241779 and parameters: {'embedding_dim': 455, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 0 with value: -571.897944241779.
+[I 2025-12-17 20:39:02,798] Trial 1 finished with value: -2963.645345402436 and parameters: {'embedding_dim': 294, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 0 with value: -571.897944241779.
+[I 2025-12-17 20:39:22,253] Trial 2 finished with value: -323.0807853187522 and parameters: {'embedding_dim': 266, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 2 with value: -323.0807853187522.
+[I 2025-12-17 20:39:39,159] Trial 3 finished with value: -651.957401119985 and parameters: {'embedding_dim': 448, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 2 with value: -323.0807853187522.
+[I 2025-12-17 20:39:53,562] Trial 4 finished with value: -260.07943161588037 and parameters: {'embedding_dim': 209, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 4 with value: -260.07943161588037.
+[I 2025-12-17 20:40:29,359] Trial 5 finished with value: -332.1606138494504 and parameters: {'embedding_dim': 366, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 4 with value: -260.07943161588037.
+[I 2025-12-17 20:40:51,902] Trial 6 finished with value: -626.5803054815773 and parameters: {'embedding_dim': 411, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 4 with value: -260.07943161588037.
+[I 2025-12-17 20:41:03,661] Trial 7 finished with value: -948.5528860186337 and parameters: {'embedding_dim': 491, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 4 with value: -260.07943161588037.
+[I 2025-12-17 20:41:45,848] Trial 8 finished with value: -292.24491029489275 and parameters: {'embedding_dim': 149, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 4 with value: -260.07943161588037.
+[I 2025-12-17 20:41:56,993] Trial 9 finished with value: -269.78776540972115 and parameters: {'embedding_dim': 281, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 4 with value: -260.07943161588037.
+[I 2025-12-17 20:42:19,698] Trial 10 finished with value: -182.80827791455295 and parameters: {'embedding_dim': 170, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 10 with value: -182.80827791455295.
+[I 2025-12-17 20:42:42,477] Trial 11 finished with value: -394.68511498956804 and parameters: {'embedding_dim': 160, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 10 with value: -182.80827791455295.
+[I 2025-12-17 20:43:05,177] Trial 12 finished with value: -1505.6794554739786 and parameters: {'embedding_dim': 210, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 10 with value: -182.80827791455295.
+[I 2025-12-17 20:43:51,159] Trial 13 finished with value: -536.9095623988236 and parameters: {'embedding_dim': 221, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 10 with value: -182.80827791455295.
+[I 2025-12-17 20:44:37,106] Trial 14 finished with value: -396.320709988775 and parameters: {'embedding_dim': 198, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 10 with value: -182.80827791455295.
+[I 2025-12-17 20:44:53,543] Trial 15 finished with value: -277.4847243160634 and parameters: {'embedding_dim': 338, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 10 with value: -182.80827791455295.
+[I 2025-12-17 20:45:15,921] Trial 16 finished with value: -270.50692421275204 and parameters: {'embedding_dim': 141, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 10 with value: -182.80827791455295.
+[I 2025-12-17 20:45:30,258] Trial 17 finished with value: -208.65533941351524 and parameters: {'embedding_dim': 255, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 10 with value: -182.80827791455295.
+[I 2025-12-17 20:46:15,920] Trial 18 finished with value: -19.68207787611027 and parameters: {'embedding_dim': 253, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 18 with value: -19.68207787611027.
+[I 2025-12-17 20:46:39,377] Trial 19 finished with value: -860.5257848527709 and parameters: {'embedding_dim': 335, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 18 with value: -19.68207787611027.
+[I 2025-12-17 20:47:37,178] Trial 20 finished with value: -52.76982362256746 and parameters: {'embedding_dim': 175, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 18 with value: -19.68207787611027.
+[I 2025-12-17 20:48:34,801] Trial 21 finished with value: -552.9687918841131 and parameters: {'embedding_dim': 177, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 18 with value: -19.68207787611027.
+[I 2025-12-17 20:49:43,892] Trial 22 finished with value: -254.99083999714725 and parameters: {'embedding_dim': 239, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 18 with value: -19.68207787611027.
+[I 2025-12-17 20:50:41,764] Trial 23 finished with value: -163.78225306578906 and parameters: {'embedding_dim': 133, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 18 with value: -19.68207787611027.
+[I 2025-12-17 20:51:38,811] Trial 24 finished with value: -201.5067868450143 and parameters: {'embedding_dim': 133, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 18 with value: -19.68207787611027.
+[I 2025-12-17 20:52:36,899] Trial 25 finished with value: -44.44827515274875 and parameters: {'embedding_dim': 238, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 18 with value: -19.68207787611027.
+[I 2025-12-17 20:53:22,572] Trial 26 finished with value: -68.57313622974397 and parameters: {'embedding_dim': 301, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 18 with value: -19.68207787611027.
+[I 2025-12-17 20:54:31,463] Trial 27 finished with value: -34.60125242104334 and parameters: {'embedding_dim': 188, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 18 with value: -19.68207787611027.
+[I 2025-12-17 20:55:41,047] Trial 28 finished with value: -406.6107567076311 and parameters: {'embedding_dim': 230, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 18 with value: -19.68207787611027.
+[I 2025-12-17 20:56:50,066] Trial 29 finished with value: -218.26841383549151 and parameters: {'embedding_dim': 364, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 18 with value: -19.68207787611027.
+[I 2025-12-17 20:57:36,906] A new study created in memory with name: no-name-563284e5-d0b9-4178-bb5d-4bd0bfe8235f
+[I 2025-12-17 20:57:40,387] Trial 0 finished with value: -112.86838662647631 and parameters: {'embedding_dim': 100, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -112.86838662647631.
+[I 2025-12-17 20:57:46,904] Trial 1 finished with value: -63.25119429277383 and parameters: {'embedding_dim': 83, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 1 with value: -63.25119429277383.
+[I 2025-12-17 20:57:54,136] Trial 2 finished with value: -7.036957705714914 and parameters: {'embedding_dim': 116, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 20:58:01,433] Trial 3 finished with value: -59.896428638052924 and parameters: {'embedding_dim': 121, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 20:58:04,829] Trial 4 finished with value: -107.93263797899615 and parameters: {'embedding_dim': 75, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 20:58:09,899] Trial 5 finished with value: -57.91818216047634 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 20:58:16,691] Trial 6 finished with value: -166.21598648462583 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 20:58:21,781] Trial 7 finished with value: -15.155278838521232 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 20:58:25,118] Trial 8 finished with value: -49.36615280691767 and parameters: {'embedding_dim': 85, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 20:58:28,610] Trial 9 finished with value: -146.2169775289128 and parameters: {'embedding_dim': 126, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 20:58:35,180] Trial 10 finished with value: -56.325735144030475 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 20:58:40,535] Trial 11 finished with value: -76.05342442799909 and parameters: {'embedding_dim': 66, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 20:58:45,917] Trial 12 finished with value: -41.87714832543831 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 20:58:50,994] Trial 13 finished with value: -13.887456022576124 and parameters: {'embedding_dim': 113, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 20:58:56,012] Trial 14 finished with value: -168.5087114464499 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 20:59:02,687] Trial 15 finished with value: -10.51294293810312 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 20:59:09,932] Trial 16 finished with value: -131.40497915028945 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 20:59:16,761] Trial 17 finished with value: -85.42367220356601 and parameters: {'embedding_dim': 126, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 20:59:23,984] Trial 18 finished with value: -19.58724150145163 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 20:59:30,582] Trial 19 finished with value: -37.70218686951584 and parameters: {'embedding_dim': 91, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 20:59:37,399] Trial 20 finished with value: -43.354358013030286 and parameters: {'embedding_dim': 105, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 20:59:42,469] Trial 21 finished with value: -33.04035546655268 and parameters: {'embedding_dim': 117, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 20:59:47,550] Trial 22 finished with value: -109.75031360644857 and parameters: {'embedding_dim': 115, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 20:59:52,624] Trial 23 finished with value: -85.21582848186252 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 20:59:59,399] Trial 24 finished with value: -16.483083274089186 and parameters: {'embedding_dim': 107, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 21:00:05,115] Trial 25 finished with value: -85.31714226252952 and parameters: {'embedding_dim': 122, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 21:00:11,976] Trial 26 finished with value: -89.99036309057539 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 21:00:17,102] Trial 27 finished with value: -54.77495848396299 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 21:00:23,666] Trial 28 finished with value: -167.963296646692 and parameters: {'embedding_dim': 122, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 21:00:27,217] Trial 29 finished with value: -27.90833643195853 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 21:00:32,605] Trial 30 finished with value: -35.33103321785672 and parameters: {'embedding_dim': 102, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 21:00:37,710] Trial 31 finished with value: -37.6967729158107 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 21:00:42,790] Trial 32 finished with value: -51.3414299730517 and parameters: {'embedding_dim': 83, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 21:00:47,884] Trial 33 finished with value: -16.51380449921858 and parameters: {'embedding_dim': 76, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 21:00:54,663] Trial 34 finished with value: -61.78498159589792 and parameters: {'embedding_dim': 123, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 21:00:59,892] Trial 35 finished with value: -44.67334955424695 and parameters: {'embedding_dim': 65, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 21:01:03,406] Trial 36 finished with value: -78.66003102974848 and parameters: {'embedding_dim': 97, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 21:01:08,466] Trial 37 finished with value: -198.8101024918054 and parameters: {'embedding_dim': 87, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -7.036957705714914.
+[I 2025-12-17 21:01:15,760] Trial 38 finished with value: -6.728554871758213 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 38 with value: -6.728554871758213.
+[I 2025-12-17 21:01:23,026] Trial 39 finished with value: -39.67531296349361 and parameters: {'embedding_dim': 109, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 38 with value: -6.728554871758213.
+[I 2025-12-17 21:01:30,296] Trial 40 finished with value: -18.737285188010603 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 38 with value: -6.728554871758213.
+[I 2025-12-17 21:01:37,578] Trial 41 finished with value: -78.16270699706381 and parameters: {'embedding_dim': 68, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 38 with value: -6.728554871758213.
+[I 2025-12-17 21:01:44,832] Trial 42 finished with value: -29.81208110288935 and parameters: {'embedding_dim': 71, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 38 with value: -6.728554871758213.
+[I 2025-12-17 21:01:52,095] Trial 43 finished with value: -69.92560950505883 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 38 with value: -6.728554871758213.
+[I 2025-12-17 21:01:59,407] Trial 44 finished with value: -9.004935099602479 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 38 with value: -6.728554871758213.
+[I 2025-12-17 21:02:06,229] Trial 45 finished with value: -77.3796046238512 and parameters: {'embedding_dim': 73, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 38 with value: -6.728554871758213.
+[I 2025-12-17 21:02:13,551] Trial 46 finished with value: -17.035007143458625 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 38 with value: -6.728554871758213.
+[I 2025-12-17 21:02:20,367] Trial 47 finished with value: -30.449013225477152 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 38 with value: -6.728554871758213.
+[I 2025-12-17 21:02:26,965] Trial 48 finished with value: -168.49471733112216 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 38 with value: -6.728554871758213.
+[I 2025-12-17 21:02:34,233] Trial 49 finished with value: -168.26912502456724 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 38 with value: -6.728554871758213.
+[I 2025-12-17 21:02:41,694] A new study created in memory with name: no-name-c0f9384f-bf13-435d-ae6d-a7f931d5d955
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_10000_2_seoul_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_10000_2_seoul_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan10000_2_seoul.csv: Class 0=9265 | Class 1=9731
+Saved ../../data/data_oversampled/ctgan10000/ctgan10000_2_seoul.csv: Class 0=9265 | Class 1=9731 | Class 2=15823
+Processing ../../data/data_for_modeling/busan_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/busan_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-17 21:02:50,711] Trial 0 finished with value: -4086.4176797430996 and parameters: {'embedding_dim': 350, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 0 with value: -4086.4176797430996.
+[I 2025-12-17 21:03:03,861] Trial 1 finished with value: -423.8530483243156 and parameters: {'embedding_dim': 308, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 1 with value: -423.8530483243156.
+[I 2025-12-17 21:03:11,056] Trial 2 finished with value: -3622.681779806086 and parameters: {'embedding_dim': 243, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 1 with value: -423.8530483243156.
+[I 2025-12-17 21:03:29,826] Trial 3 finished with value: -1192.5552409042234 and parameters: {'embedding_dim': 145, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 1 with value: -423.8530483243156.
+[I 2025-12-17 21:03:59,232] Trial 4 finished with value: -289.72995597931964 and parameters: {'embedding_dim': 147, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 4 with value: -289.72995597931964.
+[I 2025-12-17 21:04:06,364] Trial 5 finished with value: -786.7770832662925 and parameters: {'embedding_dim': 470, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 4 with value: -289.72995597931964.
+[I 2025-12-17 21:04:17,663] Trial 6 finished with value: -904.7646312081752 and parameters: {'embedding_dim': 267, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 4 with value: -289.72995597931964.
+[I 2025-12-17 21:04:30,232] Trial 7 finished with value: -389.48426854614183 and parameters: {'embedding_dim': 329, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 4 with value: -289.72995597931964.
+[I 2025-12-17 21:04:45,379] Trial 8 finished with value: -763.8314195797943 and parameters: {'embedding_dim': 353, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 4 with value: -289.72995597931964.
+[I 2025-12-17 21:05:15,532] Trial 9 finished with value: -515.7712492823613 and parameters: {'embedding_dim': 350, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 4 with value: -289.72995597931964.
+[I 2025-12-17 21:05:33,783] Trial 10 finished with value: -930.7106703567586 and parameters: {'embedding_dim': 129, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -289.72995597931964.
+[I 2025-12-17 21:05:57,292] Trial 11 finished with value: -498.31025131953413 and parameters: {'embedding_dim': 479, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -289.72995597931964.
+[I 2025-12-17 21:06:13,187] Trial 12 finished with value: -589.918805084402 and parameters: {'embedding_dim': 207, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 4 with value: -289.72995597931964.
+[I 2025-12-17 21:06:31,342] Trial 13 finished with value: -1738.705659411451 and parameters: {'embedding_dim': 437, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -289.72995597931964.
+[I 2025-12-17 21:06:44,890] Trial 14 finished with value: -337.06581967877617 and parameters: {'embedding_dim': 402, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 4 with value: -289.72995597931964.
+[I 2025-12-17 21:07:15,602] Trial 15 finished with value: -456.37743849418837 and parameters: {'embedding_dim': 412, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 4 with value: -289.72995597931964.
+[I 2025-12-17 21:07:25,378] Trial 16 finished with value: -2091.9081802938135 and parameters: {'embedding_dim': 400, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 4 with value: -289.72995597931964.
+[I 2025-12-17 21:08:00,389] Trial 17 finished with value: -228.3442369536398 and parameters: {'embedding_dim': 191, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 17 with value: -228.3442369536398.
+[I 2025-12-17 21:08:36,636] Trial 18 finished with value: -979.9099048314704 and parameters: {'embedding_dim': 181, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 17 with value: -228.3442369536398.
+[I 2025-12-17 21:09:11,982] Trial 19 finished with value: -281.24534909748525 and parameters: {'embedding_dim': 174, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 17 with value: -228.3442369536398.
+[I 2025-12-17 21:09:47,553] Trial 20 finished with value: -338.1634794302599 and parameters: {'embedding_dim': 212, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 17 with value: -228.3442369536398.
+[I 2025-12-17 21:10:22,757] Trial 21 finished with value: -983.7181291301807 and parameters: {'embedding_dim': 168, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 17 with value: -228.3442369536398.
+[I 2025-12-17 21:10:51,941] Trial 22 finished with value: -1076.093932829475 and parameters: {'embedding_dim': 245, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 17 with value: -228.3442369536398.
+[I 2025-12-17 21:11:27,265] Trial 23 finished with value: -433.33894894489896 and parameters: {'embedding_dim': 174, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 17 with value: -228.3442369536398.
+[I 2025-12-17 21:11:57,511] Trial 24 finished with value: -250.83630899037146 and parameters: {'embedding_dim': 207, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 17 with value: -228.3442369536398.
+[I 2025-12-17 21:12:32,391] Trial 25 finished with value: -526.8281942944112 and parameters: {'embedding_dim': 273, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 17 with value: -228.3442369536398.
+[I 2025-12-17 21:13:03,343] Trial 26 finished with value: -395.04212891779224 and parameters: {'embedding_dim': 221, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 17 with value: -228.3442369536398.
+[I 2025-12-17 21:13:38,057] Trial 27 finished with value: -490.0054316122895 and parameters: {'embedding_dim': 196, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 17 with value: -228.3442369536398.
+[I 2025-12-17 21:14:07,505] Trial 28 finished with value: -143.4780553949397 and parameters: {'embedding_dim': 293, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 28 with value: -143.4780553949397.
+[I 2025-12-17 21:14:20,435] Trial 29 finished with value: -901.1172981783925 and parameters: {'embedding_dim': 284, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 28 with value: -143.4780553949397.
+[I 2025-12-17 21:14:50,943] A new study created in memory with name: no-name-b1d21953-e4d9-4ad1-ad22-ee04dfef3f3e
+[I 2025-12-17 21:14:57,337] Trial 0 finished with value: -21.69043159731435 and parameters: {'embedding_dim': 118, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -21.69043159731435.
+[I 2025-12-17 21:15:02,333] Trial 1 finished with value: -4.674811431440093 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:15:05,446] Trial 2 finished with value: -4.8384873031257305 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:15:08,530] Trial 3 finished with value: -218.1396713245498 and parameters: {'embedding_dim': 117, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:15:11,638] Trial 4 finished with value: -218.88317602219524 and parameters: {'embedding_dim': 65, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:15:18,297] Trial 5 finished with value: -238.7282523254339 and parameters: {'embedding_dim': 113, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:15:25,451] Trial 6 finished with value: -36.7061455553572 and parameters: {'embedding_dim': 75, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:15:30,272] Trial 7 finished with value: -21.141694492497116 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:15:36,711] Trial 8 finished with value: -62.11584557113752 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:15:41,927] Trial 9 finished with value: -41.37087063735456 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:15:46,890] Trial 10 finished with value: -196.01269592101755 and parameters: {'embedding_dim': 128, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:15:50,227] Trial 11 finished with value: -31.812121715124427 and parameters: {'embedding_dim': 91, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:15:53,461] Trial 12 finished with value: -6.771920693163789 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:15:58,467] Trial 13 finished with value: -24.681732417047765 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:16:01,901] Trial 14 finished with value: -122.710900393848 and parameters: {'embedding_dim': 105, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:16:06,589] Trial 15 finished with value: -58.59752352838401 and parameters: {'embedding_dim': 87, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:16:09,815] Trial 16 finished with value: -37.01819522207898 and parameters: {'embedding_dim': 77, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:16:14,749] Trial 17 finished with value: -40.27458960086301 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:16:19,464] Trial 18 finished with value: -274.95523082590756 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:16:22,930] Trial 19 finished with value: -32.76592359006606 and parameters: {'embedding_dim': 97, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:16:27,651] Trial 20 finished with value: -59.26699084708872 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:16:30,937] Trial 21 finished with value: -41.29024910143705 and parameters: {'embedding_dim': 83, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:16:34,167] Trial 22 finished with value: -43.16654204518687 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:16:37,519] Trial 23 finished with value: -150.24586595042243 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:16:40,750] Trial 24 finished with value: -162.87567127113311 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:16:43,974] Trial 25 finished with value: -36.889249659588174 and parameters: {'embedding_dim': 89, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:16:48,908] Trial 26 finished with value: -15.41378558650735 and parameters: {'embedding_dim': 71, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:16:52,149] Trial 27 finished with value: -282.349961782482 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:16:57,402] Trial 28 finished with value: -188.70164303441229 and parameters: {'embedding_dim': 109, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:17:03,806] Trial 29 finished with value: -28.175654217255016 and parameters: {'embedding_dim': 124, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:17:10,221] Trial 30 finished with value: -5.404015574992943 and parameters: {'embedding_dim': 80, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:17:16,639] Trial 31 finished with value: -34.06504899901981 and parameters: {'embedding_dim': 81, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:17:23,081] Trial 32 finished with value: -68.76601959658876 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:17:29,490] Trial 33 finished with value: -34.71961141366984 and parameters: {'embedding_dim': 79, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:17:32,634] Trial 34 finished with value: -45.948269032574316 and parameters: {'embedding_dim': 118, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:17:39,043] Trial 35 finished with value: -30.621266625933497 and parameters: {'embedding_dim': 68, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:17:42,200] Trial 36 finished with value: -26.4196873105856 and parameters: {'embedding_dim': 86, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:17:47,045] Trial 37 finished with value: -13.036166339181872 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:17:53,715] Trial 38 finished with value: -71.87443831738514 and parameters: {'embedding_dim': 114, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:17:58,979] Trial 39 finished with value: -132.36943069543287 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -4.674811431440093.
+[I 2025-12-17 21:18:02,123] Trial 40 finished with value: -2.886859100526434 and parameters: {'embedding_dim': 123, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 40 with value: -2.886859100526434.
+[I 2025-12-17 21:18:05,268] Trial 41 finished with value: -33.296660752988664 and parameters: {'embedding_dim': 125, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 40 with value: -2.886859100526434.
+[I 2025-12-17 21:18:08,420] Trial 42 finished with value: -38.63005570188702 and parameters: {'embedding_dim': 121, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 40 with value: -2.886859100526434.
+[I 2025-12-17 21:18:11,554] Trial 43 finished with value: -116.37990225579325 and parameters: {'embedding_dim': 121, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 40 with value: -2.886859100526434.
+[I 2025-12-17 21:18:14,736] Trial 44 finished with value: -53.273071878192205 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 40 with value: -2.886859100526434.
+[I 2025-12-17 21:18:17,882] Trial 45 finished with value: -142.60492421870777 and parameters: {'embedding_dim': 111, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 40 with value: -2.886859100526434.
+[I 2025-12-17 21:18:22,851] Trial 46 finished with value: -107.60873799216893 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 40 with value: -2.886859100526434.
+[I 2025-12-17 21:18:25,979] Trial 47 finished with value: -55.20401256249218 and parameters: {'embedding_dim': 125, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 40 with value: -2.886859100526434.
+[I 2025-12-17 21:18:31,280] Trial 48 finished with value: -14.475406981028671 and parameters: {'embedding_dim': 116, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 40 with value: -2.886859100526434.
+[I 2025-12-17 21:18:34,511] Trial 49 finished with value: -15.401412255709703 and parameters: {'embedding_dim': 107, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 40 with value: -2.886859100526434.
+[I 2025-12-17 21:18:37,935] A new study created in memory with name: no-name-2d71249f-a2b7-4a81-9bd4-6206415c5bbb
+[I 2025-12-17 21:18:48,824] Trial 0 finished with value: -559.8898351862952 and parameters: {'embedding_dim': 137, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 0 with value: -559.8898351862952.
+[I 2025-12-17 21:18:58,290] Trial 1 finished with value: -680.6694913013756 and parameters: {'embedding_dim': 142, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 0 with value: -559.8898351862952.
+[I 2025-12-17 21:19:05,119] Trial 2 finished with value: -5936.129993307162 and parameters: {'embedding_dim': 329, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 0 with value: -559.8898351862952.
+[I 2025-12-17 21:19:10,594] Trial 3 finished with value: -1483.436182138388 and parameters: {'embedding_dim': 400, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 0 with value: -559.8898351862952.
+[I 2025-12-17 21:19:22,249] Trial 4 finished with value: -353.27424144590594 and parameters: {'embedding_dim': 348, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 4 with value: -353.27424144590594.
+[I 2025-12-17 21:19:27,488] Trial 5 finished with value: -568.1215221139057 and parameters: {'embedding_dim': 259, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 4 with value: -353.27424144590594.
+[I 2025-12-17 21:19:34,329] Trial 6 finished with value: -632.8006150967823 and parameters: {'embedding_dim': 160, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 4 with value: -353.27424144590594.
+[I 2025-12-17 21:19:45,200] Trial 7 finished with value: -717.283007945731 and parameters: {'embedding_dim': 185, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 4 with value: -353.27424144590594.
+[I 2025-12-17 21:19:58,837] Trial 8 finished with value: -328.05916119036397 and parameters: {'embedding_dim': 348, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 8 with value: -328.05916119036397.
+[I 2025-12-17 21:20:12,517] Trial 9 finished with value: -509.5836017919495 and parameters: {'embedding_dim': 144, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 8 with value: -328.05916119036397.
+[I 2025-12-17 21:20:34,937] Trial 10 finished with value: -306.223960208647 and parameters: {'embedding_dim': 490, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 10 with value: -306.223960208647.
+[I 2025-12-17 21:20:57,465] Trial 11 finished with value: -1127.331084008331 and parameters: {'embedding_dim': 506, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 10 with value: -306.223960208647.
+[I 2025-12-17 21:21:16,161] Trial 12 finished with value: -755.1898456395655 and parameters: {'embedding_dim': 501, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 10 with value: -306.223960208647.
+[I 2025-12-17 21:21:34,824] Trial 13 finished with value: -558.9244544847875 and parameters: {'embedding_dim': 432, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 10 with value: -306.223960208647.
+[I 2025-12-17 21:21:57,362] Trial 14 finished with value: -176.93882184035942 and parameters: {'embedding_dim': 441, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 14 with value: -176.93882184035942.
+[I 2025-12-17 21:22:19,915] Trial 15 finished with value: -585.4729634771522 and parameters: {'embedding_dim': 451, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 14 with value: -176.93882184035942.
+[I 2025-12-17 21:22:42,329] Trial 16 finished with value: -723.8388970320193 and parameters: {'embedding_dim': 455, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 14 with value: -176.93882184035942.
+[I 2025-12-17 21:23:04,774] Trial 17 finished with value: -519.0992422352074 and parameters: {'embedding_dim': 397, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 14 with value: -176.93882184035942.
+[I 2025-12-17 21:23:23,293] Trial 18 finished with value: -135.50552670436878 and parameters: {'embedding_dim': 292, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 18 with value: -135.50552670436878.
+[I 2025-12-17 21:23:41,766] Trial 19 finished with value: -612.3670945168567 and parameters: {'embedding_dim': 275, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 18 with value: -135.50552670436878.
+[I 2025-12-17 21:23:56,698] Trial 20 finished with value: -707.5471674381713 and parameters: {'embedding_dim': 263, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 18 with value: -135.50552670436878.
+[I 2025-12-17 21:24:19,158] Trial 21 finished with value: -277.2059534784021 and parameters: {'embedding_dim': 211, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 18 with value: -135.50552670436878.
+[I 2025-12-17 21:24:37,814] Trial 22 finished with value: -439.82010549359245 and parameters: {'embedding_dim': 222, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 18 with value: -135.50552670436878.
+[I 2025-12-17 21:25:00,216] Trial 23 finished with value: -890.1950494240632 and parameters: {'embedding_dim': 218, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 18 with value: -135.50552670436878.
+[I 2025-12-17 21:25:18,866] Trial 24 finished with value: -1256.3619528364657 and parameters: {'embedding_dim': 296, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 18 with value: -135.50552670436878.
+[I 2025-12-17 21:25:41,319] Trial 25 finished with value: -377.4040479806062 and parameters: {'embedding_dim': 222, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 18 with value: -135.50552670436878.
+[I 2025-12-17 21:26:00,142] Trial 26 finished with value: -3217.5711975889953 and parameters: {'embedding_dim': 305, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 18 with value: -135.50552670436878.
+[I 2025-12-17 21:26:22,873] Trial 27 finished with value: -348.98780274124545 and parameters: {'embedding_dim': 393, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 18 with value: -135.50552670436878.
+[I 2025-12-17 21:26:45,278] Trial 28 finished with value: -809.0862929200752 and parameters: {'embedding_dim': 186, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 18 with value: -135.50552670436878.
+[I 2025-12-17 21:27:04,037] Trial 29 finished with value: -222.92297292032688 and parameters: {'embedding_dim': 376, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 18 with value: -135.50552670436878.
+[I 2025-12-17 21:27:23,595] A new study created in memory with name: no-name-b949abb6-abe1-43da-bbf9-6ab1b125a9f7
+[I 2025-12-17 21:27:27,355] Trial 0 finished with value: -29.807842545907327 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -29.807842545907327.
+[I 2025-12-17 21:27:32,876] Trial 1 finished with value: -154.79463441195193 and parameters: {'embedding_dim': 110, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -29.807842545907327.
+[I 2025-12-17 21:27:37,859] Trial 2 finished with value: -17.369522891155384 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -17.369522891155384.
+[I 2025-12-17 21:27:43,297] Trial 3 finished with value: -55.27768959767927 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -17.369522891155384.
+[I 2025-12-17 21:27:49,947] Trial 4 finished with value: -105.83745975251065 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -17.369522891155384.
+[I 2025-12-17 21:27:56,559] Trial 5 finished with value: -34.094541261464414 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -17.369522891155384.
+[I 2025-12-17 21:28:01,685] Trial 6 finished with value: -59.2992392156232 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -17.369522891155384.
+[I 2025-12-17 21:28:08,304] Trial 7 finished with value: -177.05055360077404 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -17.369522891155384.
+[I 2025-12-17 21:28:11,629] Trial 8 finished with value: -13.045705583929639 and parameters: {'embedding_dim': 94, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 8 with value: -13.045705583929639.
+[I 2025-12-17 21:28:18,939] Trial 9 finished with value: -48.30648821536565 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 8 with value: -13.045705583929639.
+[I 2025-12-17 21:28:22,396] Trial 10 finished with value: -65.27803216809666 and parameters: {'embedding_dim': 126, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 8 with value: -13.045705583929639.
+[I 2025-12-17 21:28:25,853] Trial 11 finished with value: -17.04863812212699 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 8 with value: -13.045705583929639.
+[I 2025-12-17 21:28:29,266] Trial 12 finished with value: -27.988260436681102 and parameters: {'embedding_dim': 65, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 8 with value: -13.045705583929639.
+[I 2025-12-17 21:28:32,629] Trial 13 finished with value: -108.37795209424073 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 8 with value: -13.045705583929639.
+[I 2025-12-17 21:28:36,099] Trial 14 finished with value: -757.4709058180357 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 8 with value: -13.045705583929639.
+[I 2025-12-17 21:28:39,479] Trial 15 finished with value: -242.73597470649415 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 8 with value: -13.045705583929639.
+[I 2025-12-17 21:28:42,874] Trial 16 finished with value: -85.8962824827366 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 8 with value: -13.045705583929639.
+[I 2025-12-17 21:28:47,853] Trial 17 finished with value: -25.616752476384995 and parameters: {'embedding_dim': 118, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 8 with value: -13.045705583929639.
+[I 2025-12-17 21:28:51,192] Trial 18 finished with value: -26.43211260526107 and parameters: {'embedding_dim': 70, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 8 with value: -13.045705583929639.
+[I 2025-12-17 21:28:56,378] Trial 19 finished with value: -355.6757925023273 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 8 with value: -13.045705583929639.
+[I 2025-12-17 21:28:59,740] Trial 20 finished with value: -17.875494036702715 and parameters: {'embedding_dim': 108, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 8 with value: -13.045705583929639.
+[I 2025-12-17 21:29:04,724] Trial 21 finished with value: -291.6572228339785 and parameters: {'embedding_dim': 90, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 8 with value: -13.045705583929639.
+[I 2025-12-17 21:29:09,705] Trial 22 finished with value: -67.60153321493598 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 8 with value: -13.045705583929639.
+[I 2025-12-17 21:29:13,051] Trial 23 finished with value: -494.2357954006663 and parameters: {'embedding_dim': 94, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 8 with value: -13.045705583929639.
+[I 2025-12-17 21:29:16,390] Trial 24 finished with value: -37.28078479906842 and parameters: {'embedding_dim': 83, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 8 with value: -13.045705583929639.
+[I 2025-12-17 21:29:21,380] Trial 25 finished with value: -132.53995818361952 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 8 with value: -13.045705583929639.
+[I 2025-12-17 21:29:24,908] Trial 26 finished with value: -15.369911480193005 and parameters: {'embedding_dim': 99, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 8 with value: -13.045705583929639.
+[I 2025-12-17 21:29:28,369] Trial 27 finished with value: -10.059949874047952 and parameters: {'embedding_dim': 113, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 27 with value: -10.059949874047952.
+[I 2025-12-17 21:29:31,834] Trial 28 finished with value: -13.39248171440873 and parameters: {'embedding_dim': 114, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 27 with value: -10.059949874047952.
+[I 2025-12-17 21:29:35,216] Trial 29 finished with value: -48.36376131317589 and parameters: {'embedding_dim': 114, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 27 with value: -10.059949874047952.
+[I 2025-12-17 21:29:38,625] Trial 30 finished with value: -145.0664064022488 and parameters: {'embedding_dim': 128, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 27 with value: -10.059949874047952.
+[I 2025-12-17 21:29:42,047] Trial 31 finished with value: -57.609499826025456 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 27 with value: -10.059949874047952.
+[I 2025-12-17 21:29:45,446] Trial 32 finished with value: -122.2991242552286 and parameters: {'embedding_dim': 107, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 27 with value: -10.059949874047952.
+[I 2025-12-17 21:29:49,135] Trial 33 finished with value: -70.73536825636447 and parameters: {'embedding_dim': 112, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 27 with value: -10.059949874047952.
+[I 2025-12-17 21:29:52,566] Trial 34 finished with value: -6.878931570229571 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 34 with value: -6.878931570229571.
+[I 2025-12-17 21:29:55,983] Trial 35 finished with value: -63.65444257794164 and parameters: {'embedding_dim': 120, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 34 with value: -6.878931570229571.
+[I 2025-12-17 21:29:59,389] Trial 36 finished with value: -806.8877521531917 and parameters: {'embedding_dim': 105, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 34 with value: -6.878931570229571.
+[I 2025-12-17 21:30:04,555] Trial 37 finished with value: -115.63425834348189 and parameters: {'embedding_dim': 115, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 34 with value: -6.878931570229571.
+[I 2025-12-17 21:30:08,001] Trial 38 finished with value: -65.59722602078969 and parameters: {'embedding_dim': 124, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 34 with value: -6.878931570229571.
+[I 2025-12-17 21:30:13,545] Trial 39 finished with value: -25.26536307985607 and parameters: {'embedding_dim': 110, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 34 with value: -6.878931570229571.
+[I 2025-12-17 21:30:16,961] Trial 40 finished with value: -52.07913612933136 and parameters: {'embedding_dim': 91, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 34 with value: -6.878931570229571.
+[I 2025-12-17 21:30:20,360] Trial 41 finished with value: -12.584115707433952 and parameters: {'embedding_dim': 99, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 34 with value: -6.878931570229571.
+[I 2025-12-17 21:30:23,804] Trial 42 finished with value: -124.38716896717158 and parameters: {'embedding_dim': 101, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 34 with value: -6.878931570229571.
+[I 2025-12-17 21:30:27,396] Trial 43 finished with value: -567.1719039867155 and parameters: {'embedding_dim': 103, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 34 with value: -6.878931570229571.
+[I 2025-12-17 21:30:30,944] Trial 44 finished with value: -16.99173319921609 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 34 with value: -6.878931570229571.
+[I 2025-12-17 21:30:37,845] Trial 45 finished with value: -45.64494855642104 and parameters: {'embedding_dim': 86, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 34 with value: -6.878931570229571.
+[I 2025-12-17 21:30:41,504] Trial 46 finished with value: -8.36514792189461 and parameters: {'embedding_dim': 98, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 34 with value: -6.878931570229571.
+[I 2025-12-17 21:30:45,095] Trial 47 finished with value: -17.889860158888126 and parameters: {'embedding_dim': 98, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 34 with value: -6.878931570229571.
+[I 2025-12-17 21:30:48,672] Trial 48 finished with value: -77.57240948039988 and parameters: {'embedding_dim': 94, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 34 with value: -6.878931570229571.
+[I 2025-12-17 21:30:54,121] Trial 49 finished with value: -244.1589579514444 and parameters: {'embedding_dim': 87, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 34 with value: -6.878931570229571.
+[I 2025-12-17 21:30:57,714] A new study created in memory with name: no-name-cc0f6192-9ec8-45b2-9536-3f2e5e2788a6
+[I 2025-12-17 21:31:55,248] Trial 0 finished with value: -708.1979688828613 and parameters: {'embedding_dim': 342, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 0 with value: -708.1979688828613.
+[I 2025-12-17 21:32:15,499] Trial 1 finished with value: -1420.7455272428347 and parameters: {'embedding_dim': 343, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 0 with value: -708.1979688828613.
+[I 2025-12-17 21:32:30,178] Trial 2 finished with value: -3725.4363050210522 and parameters: {'embedding_dim': 357, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 0 with value: -708.1979688828613.
+[I 2025-12-17 21:32:51,098] Trial 3 finished with value: -689.9985149141897 and parameters: {'embedding_dim': 401, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 3 with value: -689.9985149141897.
+[I 2025-12-17 21:33:02,270] Trial 4 finished with value: -527.863545458047 and parameters: {'embedding_dim': 450, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 4 with value: -527.863545458047.
+[I 2025-12-17 21:34:11,040] Trial 5 finished with value: -412.62174630580665 and parameters: {'embedding_dim': 159, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 5 with value: -412.62174630580665.
+[I 2025-12-17 21:34:51,731] Trial 6 finished with value: -121.7701604965467 and parameters: {'embedding_dim': 421, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 6 with value: -121.7701604965467.
+[I 2025-12-17 21:35:19,815] Trial 7 finished with value: -380.726845325517 and parameters: {'embedding_dim': 214, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 6 with value: -121.7701604965467.
+[I 2025-12-17 21:35:49,809] Trial 8 finished with value: -420.1184964766047 and parameters: {'embedding_dim': 442, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 6 with value: -121.7701604965467.
+[I 2025-12-17 21:36:26,853] Trial 9 finished with value: -382.85904994537134 and parameters: {'embedding_dim': 194, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 6 with value: -121.7701604965467.
+[I 2025-12-17 21:37:06,354] Trial 10 finished with value: -89.84241787619357 and parameters: {'embedding_dim': 259, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 10 with value: -89.84241787619357.
+[I 2025-12-17 21:37:44,945] Trial 11 finished with value: -371.2997013398898 and parameters: {'embedding_dim': 284, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 10 with value: -89.84241787619357.
+[I 2025-12-17 21:38:23,608] Trial 12 finished with value: -129.4538972512578 and parameters: {'embedding_dim': 260, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 10 with value: -89.84241787619357.
+[I 2025-12-17 21:39:09,082] Trial 13 finished with value: -309.8844392133294 and parameters: {'embedding_dim': 505, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 10 with value: -89.84241787619357.
+[I 2025-12-17 21:39:46,247] Trial 14 finished with value: -2062.889750303519 and parameters: {'embedding_dim': 402, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 10 with value: -89.84241787619357.
+[I 2025-12-17 21:40:10,357] Trial 15 finished with value: -381.00255268222304 and parameters: {'embedding_dim': 296, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 10 with value: -89.84241787619357.
+[I 2025-12-17 21:40:47,356] Trial 16 finished with value: -270.9626844718249 and parameters: {'embedding_dim': 223, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 10 with value: -89.84241787619357.
+[I 2025-12-17 21:41:32,044] Trial 17 finished with value: -197.69759071514258 and parameters: {'embedding_dim': 500, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 10 with value: -89.84241787619357.
+[I 2025-12-17 21:42:21,185] Trial 18 finished with value: -187.47313046368595 and parameters: {'embedding_dim': 140, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 10 with value: -89.84241787619357.
+[I 2025-12-17 21:42:38,468] Trial 19 finished with value: -355.2010800565539 and parameters: {'embedding_dim': 390, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 10 with value: -89.84241787619357.
+[I 2025-12-17 21:43:15,150] Trial 20 finished with value: -1014.7297585655175 and parameters: {'embedding_dim': 261, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 10 with value: -89.84241787619357.
+[I 2025-12-17 21:43:53,567] Trial 21 finished with value: -498.6258574026665 and parameters: {'embedding_dim': 253, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 10 with value: -89.84241787619357.
+[I 2025-12-17 21:44:31,595] Trial 22 finished with value: -1050.9809186287778 and parameters: {'embedding_dim': 309, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 10 with value: -89.84241787619357.
+[I 2025-12-17 21:45:16,969] Trial 23 finished with value: -411.08945679882055 and parameters: {'embedding_dim': 256, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 10 with value: -89.84241787619357.
+[I 2025-12-17 21:45:58,658] Trial 24 finished with value: -207.66516411080056 and parameters: {'embedding_dim': 182, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 10 with value: -89.84241787619357.
+[I 2025-12-17 21:46:43,657] Trial 25 finished with value: -232.48847894390798 and parameters: {'embedding_dim': 241, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 10 with value: -89.84241787619357.
+[I 2025-12-17 21:47:20,187] Trial 26 finished with value: -989.483878157095 and parameters: {'embedding_dim': 284, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 10 with value: -89.84241787619357.
+[I 2025-12-17 21:48:07,037] Trial 27 finished with value: -318.13002851586333 and parameters: {'embedding_dim': 442, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 10 with value: -89.84241787619357.
+[I 2025-12-17 21:48:58,796] Trial 28 finished with value: -72.41590421367846 and parameters: {'embedding_dim': 370, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 28 with value: -72.41590421367846.
+[I 2025-12-17 21:49:48,804] Trial 29 finished with value: -2650.7708898113387 and parameters: {'embedding_dim': 340, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 28 with value: -72.41590421367846.
+[I 2025-12-17 21:50:39,410] A new study created in memory with name: no-name-bce06079-6aac-4a47-a86e-c3f72b43457e
+[I 2025-12-17 21:50:44,450] Trial 0 finished with value: -50.5275212515089 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -50.5275212515089.
+[I 2025-12-17 21:50:48,678] Trial 1 finished with value: -476.2894026396733 and parameters: {'embedding_dim': 76, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -50.5275212515089.
+[I 2025-12-17 21:50:53,940] Trial 2 finished with value: -279.6611092078164 and parameters: {'embedding_dim': 96, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -50.5275212515089.
+[I 2025-12-17 21:51:01,135] Trial 3 finished with value: -53.42627805886097 and parameters: {'embedding_dim': 80, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -50.5275212515089.
+[I 2025-12-17 21:51:06,803] Trial 4 finished with value: -38.877614105138655 and parameters: {'embedding_dim': 70, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -38.877614105138655.
+[I 2025-12-17 21:51:10,467] Trial 5 finished with value: -146.19425201743874 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 4 with value: -38.877614105138655.
+[I 2025-12-17 21:51:18,162] Trial 6 finished with value: -10.29022090093601 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 6 with value: -10.29022090093601.
+[I 2025-12-17 21:51:28,320] Trial 7 finished with value: -118.33969514060769 and parameters: {'embedding_dim': 109, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 6 with value: -10.29022090093601.
+[I 2025-12-17 21:51:33,457] Trial 8 finished with value: -316.7697978380305 and parameters: {'embedding_dim': 126, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 6 with value: -10.29022090093601.
+[I 2025-12-17 21:51:40,621] Trial 9 finished with value: -385.9415123322327 and parameters: {'embedding_dim': 96, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 6 with value: -10.29022090093601.
+[I 2025-12-17 21:51:48,272] Trial 10 finished with value: -47.87326497375033 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 6 with value: -10.29022090093601.
+[I 2025-12-17 21:51:53,892] Trial 11 finished with value: -13.259689956746197 and parameters: {'embedding_dim': 65, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 6 with value: -10.29022090093601.
+[I 2025-12-17 21:51:59,511] Trial 12 finished with value: -65.51844632437536 and parameters: {'embedding_dim': 81, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 6 with value: -10.29022090093601.
+[I 2025-12-17 21:52:07,273] Trial 13 finished with value: -102.90376420037637 and parameters: {'embedding_dim': 68, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 6 with value: -10.29022090093601.
+[I 2025-12-17 21:52:14,968] Trial 14 finished with value: -55.004018272768164 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 6 with value: -10.29022090093601.
+[I 2025-12-17 21:52:20,301] Trial 15 finished with value: -124.12662018837396 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 6 with value: -10.29022090093601.
+[I 2025-12-17 21:52:28,027] Trial 16 finished with value: -41.05686656191593 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 6 with value: -10.29022090093601.
+[I 2025-12-17 21:52:31,736] Trial 17 finished with value: -25.369774943602682 and parameters: {'embedding_dim': 68, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 6 with value: -10.29022090093601.
+[I 2025-12-17 21:52:36,861] Trial 18 finished with value: -43.25302905999006 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 6 with value: -10.29022090093601.
+[I 2025-12-17 21:52:44,271] Trial 19 finished with value: -74.86336499002365 and parameters: {'embedding_dim': 108, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 6 with value: -10.29022090093601.
+[I 2025-12-17 21:52:51,893] Trial 20 finished with value: -90.18664931706536 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 6 with value: -10.29022090093601.
+[I 2025-12-17 21:52:55,531] Trial 21 finished with value: -55.43938372014681 and parameters: {'embedding_dim': 72, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 6 with value: -10.29022090093601.
+[I 2025-12-17 21:52:59,221] Trial 22 finished with value: -159.50861314148705 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 6 with value: -10.29022090093601.
+[I 2025-12-17 21:53:02,919] Trial 23 finished with value: -9.13229823571696 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 23 with value: -9.13229823571696.
+[I 2025-12-17 21:53:06,566] Trial 24 finished with value: -268.87588098502124 and parameters: {'embedding_dim': 65, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 23 with value: -9.13229823571696.
+[I 2025-12-17 21:53:12,215] Trial 25 finished with value: -192.08288922766357 and parameters: {'embedding_dim': 79, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 23 with value: -9.13229823571696.
+[I 2025-12-17 21:53:19,918] Trial 26 finished with value: -35.462474524593816 and parameters: {'embedding_dim': 71, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 23 with value: -9.13229823571696.
+[I 2025-12-17 21:53:27,980] Trial 27 finished with value: -27.00065567137133 and parameters: {'embedding_dim': 88, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 23 with value: -9.13229823571696.
+[I 2025-12-17 21:53:31,401] Trial 28 finished with value: -32.681473913843135 and parameters: {'embedding_dim': 117, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 23 with value: -9.13229823571696.
+[I 2025-12-17 21:53:34,871] Trial 29 finished with value: -140.05388371862077 and parameters: {'embedding_dim': 91, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 23 with value: -9.13229823571696.
+[I 2025-12-17 21:53:42,454] Trial 30 finished with value: -7.407216102548917 and parameters: {'embedding_dim': 68, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 30 with value: -7.407216102548917.
+[I 2025-12-17 21:53:50,171] Trial 31 finished with value: -31.258249996239158 and parameters: {'embedding_dim': 67, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 30 with value: -7.407216102548917.
+[I 2025-12-17 21:53:57,776] Trial 32 finished with value: -144.34044668053554 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 30 with value: -7.407216102548917.
+[I 2025-12-17 21:54:05,397] Trial 33 finished with value: -45.00394054985919 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 30 with value: -7.407216102548917.
+[I 2025-12-17 21:54:12,307] Trial 34 finished with value: -112.5901180977053 and parameters: {'embedding_dim': 83, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 30 with value: -7.407216102548917.
+[I 2025-12-17 21:54:22,544] Trial 35 finished with value: -58.15270736329073 and parameters: {'embedding_dim': 71, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 30 with value: -7.407216102548917.
+[I 2025-12-17 21:54:28,284] Trial 36 finished with value: -4.593711801778364 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 36 with value: -4.593711801778364.
+[I 2025-12-17 21:54:35,245] Trial 37 finished with value: -287.1883715130281 and parameters: {'embedding_dim': 74, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 36 with value: -4.593711801778364.
+[I 2025-12-17 21:54:39,992] Trial 38 finished with value: -17.430127733559065 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 36 with value: -4.593711801778364.
+[I 2025-12-17 21:54:46,957] Trial 39 finished with value: -200.84688797596954 and parameters: {'embedding_dim': 68, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 36 with value: -4.593711801778364.
+[I 2025-12-17 21:54:52,338] Trial 40 finished with value: -57.34460326099531 and parameters: {'embedding_dim': 77, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 36 with value: -4.593711801778364.
+[I 2025-12-17 21:54:58,533] Trial 41 finished with value: -56.07659565590812 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 36 with value: -4.593711801778364.
+[I 2025-12-17 21:55:04,231] Trial 42 finished with value: -202.00572201220467 and parameters: {'embedding_dim': 70, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 36 with value: -4.593711801778364.
+[I 2025-12-17 21:55:09,892] Trial 43 finished with value: -131.18807742329656 and parameters: {'embedding_dim': 67, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 36 with value: -4.593711801778364.
+[I 2025-12-17 21:55:17,616] Trial 44 finished with value: -6.4792984891074346 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 36 with value: -4.593711801778364.
+[I 2025-12-17 21:55:25,333] Trial 45 finished with value: -37.36046837312799 and parameters: {'embedding_dim': 81, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 36 with value: -4.593711801778364.
+[I 2025-12-17 21:55:30,968] Trial 46 finished with value: -99.05703524005209 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 36 with value: -4.593711801778364.
+[I 2025-12-17 21:55:36,696] Trial 47 finished with value: -44.969318851274956 and parameters: {'embedding_dim': 99, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 36 with value: -4.593711801778364.
+[I 2025-12-17 21:55:44,361] Trial 48 finished with value: -90.7508749050203 and parameters: {'embedding_dim': 70, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 36 with value: -4.593711801778364.
+[I 2025-12-17 21:55:47,853] Trial 49 finished with value: -182.5270733323744 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 36 with value: -4.593711801778364.
+[I 2025-12-17 21:55:53,707] A new study created in memory with name: no-name-eb2d1b5a-f865-4fea-b04e-3d0cdbef579e
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_10000_2_busan_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_10000_2_busan_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan10000_2_busan.csv: Class 0=9697 | Class 1=9097
+Saved ../../data/data_oversampled/ctgan10000/ctgan10000_2_busan.csv: Class 0=9697 | Class 1=9097 | Class 2=16457
+Processing ../../data/data_for_modeling/daegu_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/daegu_train.csv: Optimizing CTGAN for class 1...
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_10000_2_daegu_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_10000_2_daegu_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan10000_2_daegu.csv: Class 0=9007 | Class 1=8995
+Saved ../../data/data_oversampled/ctgan10000/ctgan10000_2_daegu.csv: Class 0=9007 | Class 1=8995 | Class 2=16803
+Processing ../../data/data_for_modeling/daejeon_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/daejeon_train.csv: Optimizing CTGAN for class 1...
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_10000_2_daejeon_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_10000_2_daejeon_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan10000_2_daejeon.csv: Class 0=9146 | Class 1=9746
+Saved ../../data/data_oversampled/ctgan10000/ctgan10000_2_daejeon.csv: Class 0=9146 | Class 1=9746 | Class 2=15717
+Processing ../../data/data_for_modeling/gwangju_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/gwangju_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-17 21:56:11,942] Trial 0 finished with value: -1006.7397500193697 and parameters: {'embedding_dim': 293, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 0 with value: -1006.7397500193697.
+[I 2025-12-17 21:56:30,113] Trial 1 finished with value: -530.8596696679092 and parameters: {'embedding_dim': 316, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 1 with value: -530.8596696679092.
+[I 2025-12-17 21:56:39,106] Trial 2 finished with value: -1091.0001732814285 and parameters: {'embedding_dim': 455, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 1 with value: -530.8596696679092.
+[I 2025-12-17 21:57:39,305] Trial 3 finished with value: -856.109889111029 and parameters: {'embedding_dim': 130, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 1 with value: -530.8596696679092.
+[I 2025-12-17 21:57:54,112] Trial 4 finished with value: -948.4058909662 and parameters: {'embedding_dim': 412, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 1 with value: -530.8596696679092.
+[I 2025-12-17 21:58:38,289] Trial 5 finished with value: -1037.8942500804944 and parameters: {'embedding_dim': 384, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 1 with value: -530.8596696679092.
+[I 2025-12-17 21:58:58,828] Trial 6 finished with value: -696.2051468226254 and parameters: {'embedding_dim': 344, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 1 with value: -530.8596696679092.
+[I 2025-12-17 21:59:14,270] Trial 7 finished with value: -624.4202169232775 and parameters: {'embedding_dim': 197, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 1 with value: -530.8596696679092.
+[I 2025-12-17 21:59:57,730] Trial 8 finished with value: -652.1316934011923 and parameters: {'embedding_dim': 316, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 1 with value: -530.8596696679092.
+[I 2025-12-17 22:00:18,483] Trial 9 finished with value: -530.6290576292291 and parameters: {'embedding_dim': 327, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 9 with value: -530.6290576292291.
+[I 2025-12-17 22:01:06,900] Trial 10 finished with value: -1686.331325628612 and parameters: {'embedding_dim': 493, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 9 with value: -530.6290576292291.
+[I 2025-12-17 22:01:25,034] Trial 11 finished with value: -387.6942514039746 and parameters: {'embedding_dim': 237, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 11 with value: -387.6942514039746.
+[I 2025-12-17 22:01:43,465] Trial 12 finished with value: -554.8207561207639 and parameters: {'embedding_dim': 239, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 11 with value: -387.6942514039746.
+[I 2025-12-17 22:02:01,772] Trial 13 finished with value: -735.4681516505094 and parameters: {'embedding_dim': 241, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 11 with value: -387.6942514039746.
+[I 2025-12-17 22:02:22,498] Trial 14 finished with value: -499.4234659968031 and parameters: {'embedding_dim': 247, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 11 with value: -387.6942514039746.
+[I 2025-12-17 22:02:34,473] Trial 15 finished with value: -321.25842307291606 and parameters: {'embedding_dim': 134, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 15 with value: -321.25842307291606.
+[I 2025-12-17 22:03:10,432] Trial 16 finished with value: -835.0854734266263 and parameters: {'embedding_dim': 135, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -321.25842307291606.
+[I 2025-12-17 22:03:21,898] Trial 17 finished with value: -446.2339179175228 and parameters: {'embedding_dim': 182, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 15 with value: -321.25842307291606.
+[I 2025-12-17 22:03:37,595] Trial 18 finished with value: -1364.7581363191139 and parameters: {'embedding_dim': 182, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 15 with value: -321.25842307291606.
+[I 2025-12-17 22:04:14,388] Trial 19 finished with value: -867.6668094028271 and parameters: {'embedding_dim': 208, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -321.25842307291606.
+[I 2025-12-17 22:04:29,143] Trial 20 finished with value: -404.31596630005356 and parameters: {'embedding_dim': 271, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 15 with value: -321.25842307291606.
+[I 2025-12-17 22:04:43,553] Trial 21 finished with value: -736.5370113054897 and parameters: {'embedding_dim': 282, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 15 with value: -321.25842307291606.
+[I 2025-12-17 22:04:55,400] Trial 22 finished with value: -1827.0964906839092 and parameters: {'embedding_dim': 161, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 15 with value: -321.25842307291606.
+[I 2025-12-17 22:05:07,415] Trial 23 finished with value: -1449.6825193386135 and parameters: {'embedding_dim': 257, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 15 with value: -321.25842307291606.
+[I 2025-12-17 22:05:24,873] Trial 24 finished with value: -411.30075515401796 and parameters: {'embedding_dim': 218, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 15 with value: -321.25842307291606.
+[I 2025-12-17 22:05:40,371] Trial 25 finished with value: -821.2647915180393 and parameters: {'embedding_dim': 359, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 15 with value: -321.25842307291606.
+[I 2025-12-17 22:05:55,553] Trial 26 finished with value: -666.8577785570742 and parameters: {'embedding_dim': 275, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 15 with value: -321.25842307291606.
+[I 2025-12-17 22:06:07,766] Trial 27 finished with value: -880.0502359508376 and parameters: {'embedding_dim': 169, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 15 with value: -321.25842307291606.
+[I 2025-12-17 22:06:44,411] Trial 28 finished with value: -352.51538378728094 and parameters: {'embedding_dim': 220, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 15 with value: -321.25842307291606.
+[I 2025-12-17 22:07:21,239] Trial 29 finished with value: -384.46174263780614 and parameters: {'embedding_dim': 146, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 15 with value: -321.25842307291606.
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_10000_2_gwangju_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_10000_2_gwangju_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan10000_2_gwangju.csv: Class 0=8547 | Class 1=8799
+Saved ../../data/data_oversampled/ctgan10000/ctgan10000_2_gwangju.csv: Class 0=8547 | Class 1=8799 | Class 2=15760
+
+Running ctgan_sample_10000_3.py...
+[I 2025-12-17 22:07:36,371] A new study created in memory with name: no-name-760984de-b252-4820-89e5-f6a1da48bfba
+[I 2025-12-17 22:07:49,938] Trial 0 finished with value: -56.26941877203929 and parameters: {'embedding_dim': 84, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -56.26941877203929.
+[I 2025-12-17 22:08:02,578] Trial 1 finished with value: -192.4658485149183 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -56.26941877203929.
+[I 2025-12-17 22:08:16,952] Trial 2 finished with value: -2.9851171845946194 and parameters: {'embedding_dim': 101, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -2.9851171845946194.
+[I 2025-12-17 22:08:21,098] Trial 3 finished with value: -175.17458753029095 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -2.9851171845946194.
+[I 2025-12-17 22:08:47,750] Trial 4 finished with value: -4.143860611418836 and parameters: {'embedding_dim': 74, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -2.9851171845946194.
+[I 2025-12-17 22:09:00,649] Trial 5 finished with value: -8.882857215723257 and parameters: {'embedding_dim': 98, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 2 with value: -2.9851171845946194.
+[I 2025-12-17 22:09:14,899] Trial 6 finished with value: -9.863578249106093 and parameters: {'embedding_dim': 91, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -2.9851171845946194.
+[I 2025-12-17 22:09:21,905] Trial 7 finished with value: -12.263465486786878 and parameters: {'embedding_dim': 116, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -2.9851171845946194.
+[I 2025-12-17 22:09:28,925] Trial 8 finished with value: -14.215006443861547 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -2.9851171845946194.
+[I 2025-12-17 22:09:48,616] Trial 9 finished with value: -5.171060232078885 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -2.9851171845946194.
+[I 2025-12-17 22:09:54,754] Trial 10 finished with value: -39.138568676258735 and parameters: {'embedding_dim': 106, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -2.9851171845946194.
+[I 2025-12-17 22:10:09,167] Trial 11 finished with value: -95.70229823619918 and parameters: {'embedding_dim': 73, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -2.9851171845946194.
+[I 2025-12-17 22:10:35,948] Trial 12 finished with value: -41.5005934692845 and parameters: {'embedding_dim': 107, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -2.9851171845946194.
+[I 2025-12-17 22:10:50,312] Trial 13 finished with value: -50.55405235843885 and parameters: {'embedding_dim': 85, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -2.9851171845946194.
+[I 2025-12-17 22:10:56,554] Trial 14 finished with value: -270.87710688659655 and parameters: {'embedding_dim': 106, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -2.9851171845946194.
+[I 2025-12-17 22:11:23,331] Trial 15 finished with value: -61.682129340956934 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -2.9851171845946194.
+[I 2025-12-17 22:11:37,775] Trial 16 finished with value: -115.27250686380515 and parameters: {'embedding_dim': 67, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -2.9851171845946194.
+[I 2025-12-17 22:11:57,546] Trial 17 finished with value: -4.719293541298122 and parameters: {'embedding_dim': 81, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -2.9851171845946194.
+[I 2025-12-17 22:12:12,103] Trial 18 finished with value: -40.3513489857861 and parameters: {'embedding_dim': 91, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -2.9851171845946194.
+[I 2025-12-17 22:12:18,312] Trial 19 finished with value: -73.63102187114961 and parameters: {'embedding_dim': 99, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -2.9851171845946194.
+[I 2025-12-17 22:12:32,668] Trial 20 finished with value: -11.931820875241273 and parameters: {'embedding_dim': 113, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -2.9851171845946194.
+[I 2025-12-17 22:12:53,044] Trial 21 finished with value: -12.650982820431341 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -2.9851171845946194.
+[I 2025-12-17 22:13:14,279] Trial 22 finished with value: -13.411544796700987 and parameters: {'embedding_dim': 83, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -2.9851171845946194.
+[I 2025-12-17 22:13:33,993] Trial 23 finished with value: -0.06652041619753972 and parameters: {'embedding_dim': 71, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:13:55,314] Trial 24 finished with value: -7.694436620121958 and parameters: {'embedding_dim': 70, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:14:23,173] Trial 25 finished with value: -228.9287453140993 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:14:44,359] Trial 26 finished with value: -32.02128438352151 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:15:13,342] Trial 27 finished with value: -70.12406381501168 and parameters: {'embedding_dim': 65, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:15:24,186] Trial 28 finished with value: -271.8429828421324 and parameters: {'embedding_dim': 88, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:15:34,924] Trial 29 finished with value: -49.771226315562174 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:16:03,383] Trial 30 finished with value: -15.599846647102162 and parameters: {'embedding_dim': 102, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:16:25,559] Trial 31 finished with value: -72.16267507119791 and parameters: {'embedding_dim': 81, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:16:47,284] Trial 32 finished with value: -121.98348236022267 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:17:08,455] Trial 33 finished with value: -16.146820481905124 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:17:29,640] Trial 34 finished with value: -371.1021743359167 and parameters: {'embedding_dim': 75, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:17:42,454] Trial 35 finished with value: -87.15563121208696 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:17:57,792] Trial 36 finished with value: -630.6246513294875 and parameters: {'embedding_dim': 65, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:18:12,124] Trial 37 finished with value: -21.217602875465943 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:18:33,886] Trial 38 finished with value: -35.09309892351009 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:18:40,054] Trial 39 finished with value: -109.94335597433789 and parameters: {'embedding_dim': 94, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:18:47,033] Trial 40 finished with value: -83.26104416068071 and parameters: {'embedding_dim': 101, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:19:08,325] Trial 41 finished with value: -53.38867696797438 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:19:29,639] Trial 42 finished with value: -14.301140133357203 and parameters: {'embedding_dim': 70, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:19:50,650] Trial 43 finished with value: -3.4478235067037657 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:20:12,325] Trial 44 finished with value: -55.577407985521745 and parameters: {'embedding_dim': 88, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:20:34,149] Trial 45 finished with value: -11.325614586962361 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:20:55,285] Trial 46 finished with value: -55.47626255225204 and parameters: {'embedding_dim': 68, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:21:12,197] Trial 47 finished with value: -29.219690400009174 and parameters: {'embedding_dim': 112, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:21:21,080] Trial 48 finished with value: -89.34472350336587 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:21:36,144] Trial 49 finished with value: -82.86653144876115 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 23 with value: -0.06652041619753972.
+[I 2025-12-17 22:21:56,135] A new study created in memory with name: no-name-d43b15c6-5080-46b8-afd6-6ba3b72a7265
+Using device: cuda
+Processing ../../data/data_for_modeling/incheon_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/incheon_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-17 22:23:04,792] Trial 0 finished with value: -267.4413307738296 and parameters: {'embedding_dim': 191, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -267.4413307738296.
+[I 2025-12-17 22:23:43,221] Trial 1 finished with value: -885.4324322140491 and parameters: {'embedding_dim': 469, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 0 with value: -267.4413307738296.
+[I 2025-12-17 22:24:19,026] Trial 2 finished with value: -1061.3300754310858 and parameters: {'embedding_dim': 218, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 0 with value: -267.4413307738296.
+[I 2025-12-17 22:25:46,562] Trial 3 finished with value: -16.74012753437983 and parameters: {'embedding_dim': 257, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 3 with value: -16.74012753437983.
+[I 2025-12-17 22:26:00,850] Trial 4 finished with value: -684.697682654039 and parameters: {'embedding_dim': 224, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 3 with value: -16.74012753437983.
+[I 2025-12-17 22:26:41,417] Trial 5 finished with value: -641.1297943298055 and parameters: {'embedding_dim': 233, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 3 with value: -16.74012753437983.
+[I 2025-12-17 22:27:29,960] Trial 6 finished with value: -89.033414391361 and parameters: {'embedding_dim': 257, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 3 with value: -16.74012753437983.
+[I 2025-12-17 22:29:29,438] Trial 7 finished with value: -59.0283499990409 and parameters: {'embedding_dim': 389, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 3 with value: -16.74012753437983.
+[I 2025-12-17 22:30:40,960] Trial 8 finished with value: -407.45445397371566 and parameters: {'embedding_dim': 405, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 3 with value: -16.74012753437983.
+[I 2025-12-17 22:32:39,899] Trial 9 finished with value: -411.81777197549843 and parameters: {'embedding_dim': 187, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 3 with value: -16.74012753437983.
+[I 2025-12-17 22:33:59,266] Trial 10 finished with value: -805.1278963961354 and parameters: {'embedding_dim': 129, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 3 with value: -16.74012753437983.
+[I 2025-12-17 22:35:35,278] Trial 11 finished with value: -11.54417560095164 and parameters: {'embedding_dim': 339, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 11 with value: -11.54417560095164.
+[I 2025-12-17 22:37:09,811] Trial 12 finished with value: -260.09856636471767 and parameters: {'embedding_dim': 317, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 11 with value: -11.54417560095164.
+[I 2025-12-17 22:38:44,792] Trial 13 finished with value: -73.75783615512543 and parameters: {'embedding_dim': 308, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 11 with value: -11.54417560095164.
+[I 2025-12-17 22:40:00,896] Trial 14 finished with value: -835.6929670391706 and parameters: {'embedding_dim': 389, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 11 with value: -11.54417560095164.
+[I 2025-12-17 22:40:20,360] Trial 15 finished with value: -559.3747262644654 and parameters: {'embedding_dim': 286, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 11 with value: -11.54417560095164.
+[I 2025-12-17 22:41:56,144] Trial 16 finished with value: -71.24607548784414 and parameters: {'embedding_dim': 338, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 11 with value: -11.54417560095164.
+[I 2025-12-17 22:43:30,792] Trial 17 finished with value: -13.999574763212483 and parameters: {'embedding_dim': 471, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 11 with value: -11.54417560095164.
+[I 2025-12-17 22:44:03,023] Trial 18 finished with value: -319.33382752116637 and parameters: {'embedding_dim': 510, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 11 with value: -11.54417560095164.
+[I 2025-12-17 22:45:11,709] Trial 19 finished with value: -19.117844340535182 and parameters: {'embedding_dim': 446, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 11 with value: -11.54417560095164.
+[I 2025-12-17 22:46:50,545] Trial 20 finished with value: -382.7552395188318 and parameters: {'embedding_dim': 345, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 11 with value: -11.54417560095164.
+[I 2025-12-17 22:48:09,933] Trial 21 finished with value: -301.4304267908674 and parameters: {'embedding_dim': 273, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 11 with value: -11.54417560095164.
+[I 2025-12-17 22:49:28,301] Trial 22 finished with value: -37.02395038346476 and parameters: {'embedding_dim': 434, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 11 with value: -11.54417560095164.
+[I 2025-12-17 22:50:46,812] Trial 23 finished with value: -191.35270798229877 and parameters: {'embedding_dim': 505, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 11 with value: -11.54417560095164.
+[I 2025-12-17 22:52:24,947] Trial 24 finished with value: -39.047846244439974 and parameters: {'embedding_dim': 132, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 11 with value: -11.54417560095164.
+[I 2025-12-17 22:53:28,310] Trial 25 finished with value: -168.69017362068004 and parameters: {'embedding_dim': 355, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -11.54417560095164.
+[I 2025-12-17 22:55:06,863] Trial 26 finished with value: -593.9249741301853 and parameters: {'embedding_dim': 471, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 11 with value: -11.54417560095164.
+[I 2025-12-17 22:57:10,446] Trial 27 finished with value: -152.4616502022647 and parameters: {'embedding_dim': 367, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 11 with value: -11.54417560095164.
+[I 2025-12-17 22:58:15,333] Trial 28 finished with value: -177.6314307150453 and parameters: {'embedding_dim': 291, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 11 with value: -11.54417560095164.
+[I 2025-12-17 22:58:41,094] Trial 29 finished with value: -537.9062759600275 and parameters: {'embedding_dim': 161, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 11 with value: -11.54417560095164.
+[I 2025-12-17 23:00:24,408] A new study created in memory with name: no-name-ae097bb5-bc27-4045-9655-5b8a6e058511
+[I 2025-12-17 23:00:31,074] Trial 0 finished with value: -275.25943121540945 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -275.25943121540945.
+[I 2025-12-17 23:00:38,196] Trial 1 finished with value: -306.5509731779372 and parameters: {'embedding_dim': 114, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -275.25943121540945.
+[I 2025-12-17 23:00:43,086] Trial 2 finished with value: -125.41783261738794 and parameters: {'embedding_dim': 109, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -125.41783261738794.
+[I 2025-12-17 23:00:46,657] Trial 3 finished with value: -272.01720157268807 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -125.41783261738794.
+[I 2025-12-17 23:00:53,468] Trial 4 finished with value: -366.9035209554515 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -125.41783261738794.
+[I 2025-12-17 23:01:00,936] Trial 5 finished with value: -93.8548311744224 and parameters: {'embedding_dim': 122, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -93.8548311744224.
+[I 2025-12-17 23:01:07,344] Trial 6 finished with value: -158.1543915644458 and parameters: {'embedding_dim': 76, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 5 with value: -93.8548311744224.
+[I 2025-12-17 23:01:12,053] Trial 7 finished with value: -276.6496014299127 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 5 with value: -93.8548311744224.
+[I 2025-12-17 23:01:17,296] Trial 8 finished with value: -159.21643237070526 and parameters: {'embedding_dim': 69, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -93.8548311744224.
+[I 2025-12-17 23:01:20,420] Trial 9 finished with value: -404.5921134978274 and parameters: {'embedding_dim': 118, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 5 with value: -93.8548311744224.
+[I 2025-12-17 23:01:23,797] Trial 10 finished with value: -113.79935764441149 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 5 with value: -93.8548311744224.
+[I 2025-12-17 23:01:27,154] Trial 11 finished with value: -92.6610919296976 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 11 with value: -92.6610919296976.
+[I 2025-12-17 23:01:30,535] Trial 12 finished with value: -155.95690309200018 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 11 with value: -92.6610919296976.
+[I 2025-12-17 23:01:35,787] Trial 13 finished with value: -400.6492997816729 and parameters: {'embedding_dim': 120, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -92.6610919296976.
+[I 2025-12-17 23:01:39,144] Trial 14 finished with value: -196.1719881645416 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 11 with value: -92.6610919296976.
+[I 2025-12-17 23:01:44,377] Trial 15 finished with value: -317.3445059505549 and parameters: {'embedding_dim': 122, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -92.6610919296976.
+[I 2025-12-17 23:01:47,694] Trial 16 finished with value: -184.21291730875467 and parameters: {'embedding_dim': 110, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 11 with value: -92.6610919296976.
+[I 2025-12-17 23:01:52,921] Trial 17 finished with value: -677.4612456908511 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -92.6610919296976.
+[I 2025-12-17 23:01:57,915] Trial 18 finished with value: -156.32053386425716 and parameters: {'embedding_dim': 86, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 11 with value: -92.6610919296976.
+[I 2025-12-17 23:02:01,135] Trial 19 finished with value: -598.0484204165897 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 11 with value: -92.6610919296976.
+[I 2025-12-17 23:02:06,441] Trial 20 finished with value: -512.2059625888802 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -92.6610919296976.
+[I 2025-12-17 23:02:09,792] Trial 21 finished with value: -140.68896244999758 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 11 with value: -92.6610919296976.
+[I 2025-12-17 23:02:13,130] Trial 22 finished with value: -132.87247121744394 and parameters: {'embedding_dim': 123, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 11 with value: -92.6610919296976.
+[I 2025-12-17 23:02:19,126] Trial 23 finished with value: -128.91913082118495 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 11 with value: -92.6610919296976.
+[I 2025-12-17 23:02:23,243] Trial 24 finished with value: -34.718075869138744 and parameters: {'embedding_dim': 124, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 24 with value: -34.718075869138744.
+[I 2025-12-17 23:02:26,674] Trial 25 finished with value: -389.65467900251565 and parameters: {'embedding_dim': 123, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 24 with value: -34.718075869138744.
+[I 2025-12-17 23:02:32,028] Trial 26 finished with value: -87.3137703670926 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -34.718075869138744.
+[I 2025-12-17 23:02:35,481] Trial 27 finished with value: -363.34556341304767 and parameters: {'embedding_dim': 115, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 24 with value: -34.718075869138744.
+[I 2025-12-17 23:02:40,463] Trial 28 finished with value: -655.7393680181431 and parameters: {'embedding_dim': 105, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -34.718075869138744.
+[I 2025-12-17 23:02:46,824] Trial 29 finished with value: -445.38943562351 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 24 with value: -34.718075869138744.
+[I 2025-12-17 23:02:53,552] Trial 30 finished with value: -159.08091490642045 and parameters: {'embedding_dim': 86, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 24 with value: -34.718075869138744.
+[I 2025-12-17 23:02:58,807] Trial 31 finished with value: -178.18252071031887 and parameters: {'embedding_dim': 122, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -34.718075869138744.
+[I 2025-12-17 23:03:04,076] Trial 32 finished with value: -25.463141310395496 and parameters: {'embedding_dim': 116, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -25.463141310395496.
+[I 2025-12-17 23:03:09,374] Trial 33 finished with value: -136.63958445643277 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -25.463141310395496.
+[I 2025-12-17 23:03:16,502] Trial 34 finished with value: -164.2097847965012 and parameters: {'embedding_dim': 116, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 32 with value: -25.463141310395496.
+[I 2025-12-17 23:03:23,890] Trial 35 finished with value: -317.4753237642326 and parameters: {'embedding_dim': 100, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -25.463141310395496.
+[I 2025-12-17 23:03:27,396] Trial 36 finished with value: -499.67063424366995 and parameters: {'embedding_dim': 108, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 32 with value: -25.463141310395496.
+[I 2025-12-17 23:03:32,315] Trial 37 finished with value: -283.8213163862726 and parameters: {'embedding_dim': 125, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 32 with value: -25.463141310395496.
+[I 2025-12-17 23:03:39,521] Trial 38 finished with value: -253.5634320779779 and parameters: {'embedding_dim': 118, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 32 with value: -25.463141310395496.
+[I 2025-12-17 23:03:44,862] Trial 39 finished with value: -296.1185134115258 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 32 with value: -25.463141310395496.
+[I 2025-12-17 23:03:51,472] Trial 40 finished with value: -253.8956063775709 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 32 with value: -25.463141310395496.
+[I 2025-12-17 23:03:56,683] Trial 41 finished with value: -217.65141878015154 and parameters: {'embedding_dim': 125, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -25.463141310395496.
+[I 2025-12-17 23:04:01,918] Trial 42 finished with value: -48.816313573645346 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -25.463141310395496.
+[I 2025-12-17 23:04:07,139] Trial 43 finished with value: -155.92911337728566 and parameters: {'embedding_dim': 112, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -25.463141310395496.
+[I 2025-12-17 23:04:12,364] Trial 44 finished with value: -417.81293908869463 and parameters: {'embedding_dim': 108, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -25.463141310395496.
+[I 2025-12-17 23:04:17,577] Trial 45 finished with value: -177.4188411536899 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 32 with value: -25.463141310395496.
+[I 2025-12-17 23:04:20,907] Trial 46 finished with value: -509.0804875536929 and parameters: {'embedding_dim': 116, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 32 with value: -25.463141310395496.
+[I 2025-12-17 23:04:28,028] Trial 47 finished with value: -415.50201016106433 and parameters: {'embedding_dim': 99, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 32 with value: -25.463141310395496.
+[I 2025-12-17 23:04:32,706] Trial 48 finished with value: -485.8986953785701 and parameters: {'embedding_dim': 126, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 32 with value: -25.463141310395496.
+[I 2025-12-17 23:04:36,034] Trial 49 finished with value: -958.9887366083758 and parameters: {'embedding_dim': 121, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 32 with value: -25.463141310395496.
+[I 2025-12-17 23:04:41,447] A new study created in memory with name: no-name-06fa0414-da1e-4ded-bf0b-67fae133887a
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_10000_3_incheon_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_10000_3_incheon_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan10000_3_incheon.csv: Class 0=9324 | Class 1=9772
+Saved ../../data/data_oversampled/ctgan10000/ctgan10000_3_incheon.csv: Class 0=9324 | Class 1=9772 | Class 2=14595
+Processing ../../data/data_for_modeling/seoul_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/seoul_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-17 23:05:04,220] Trial 0 finished with value: -375.7854096414811 and parameters: {'embedding_dim': 203, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 0 with value: -375.7854096414811.
+[I 2025-12-17 23:05:19,334] Trial 1 finished with value: -1226.8419067185882 and parameters: {'embedding_dim': 443, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 0 with value: -375.7854096414811.
+[I 2025-12-17 23:05:29,426] Trial 2 finished with value: -2926.658944003611 and parameters: {'embedding_dim': 365, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 0 with value: -375.7854096414811.
+[I 2025-12-17 23:06:01,622] Trial 3 finished with value: -1095.6207702539396 and parameters: {'embedding_dim': 471, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 0 with value: -375.7854096414811.
+[I 2025-12-17 23:06:18,601] Trial 4 finished with value: -623.2936205111614 and parameters: {'embedding_dim': 305, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 0 with value: -375.7854096414811.
+[I 2025-12-17 23:06:41,484] Trial 5 finished with value: -475.9202262218637 and parameters: {'embedding_dim': 207, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 0 with value: -375.7854096414811.
+[I 2025-12-17 23:07:02,794] Trial 6 finished with value: -2433.263253354861 and parameters: {'embedding_dim': 245, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 0 with value: -375.7854096414811.
+[I 2025-12-17 23:07:28,912] Trial 7 finished with value: -510.5882801290197 and parameters: {'embedding_dim': 448, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -375.7854096414811.
+[I 2025-12-17 23:07:37,278] Trial 8 finished with value: -467.33831257849323 and parameters: {'embedding_dim': 283, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 0 with value: -375.7854096414811.
+[I 2025-12-17 23:07:45,947] Trial 9 finished with value: -281.0296857868007 and parameters: {'embedding_dim': 170, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 9 with value: -281.0296857868007.
+[I 2025-12-17 23:08:24,146] Trial 10 finished with value: -165.4587448704413 and parameters: {'embedding_dim': 143, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -165.4587448704413.
+[I 2025-12-17 23:09:00,196] Trial 11 finished with value: -810.8905686915365 and parameters: {'embedding_dim': 144, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -165.4587448704413.
+[I 2025-12-17 23:09:38,912] Trial 12 finished with value: -999.4943099383521 and parameters: {'embedding_dim': 133, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -165.4587448704413.
+[I 2025-12-17 23:10:16,948] Trial 13 finished with value: -365.8983667190632 and parameters: {'embedding_dim': 180, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -165.4587448704413.
+[I 2025-12-17 23:10:53,931] Trial 14 finished with value: -635.5836631303115 and parameters: {'embedding_dim': 368, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 10 with value: -165.4587448704413.
+[I 2025-12-17 23:11:11,159] Trial 15 finished with value: -525.3225350278974 and parameters: {'embedding_dim': 251, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 10 with value: -165.4587448704413.
+[I 2025-12-17 23:11:33,663] Trial 16 finished with value: -33.283180595619186 and parameters: {'embedding_dim': 174, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 16 with value: -33.283180595619186.
+[I 2025-12-17 23:12:23,107] Trial 17 finished with value: -51.48102533822736 and parameters: {'embedding_dim': 226, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 16 with value: -33.283180595619186.
+[I 2025-12-17 23:13:22,980] Trial 18 finished with value: -608.9316780686972 and parameters: {'embedding_dim': 237, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 16 with value: -33.283180595619186.
+[I 2025-12-17 23:14:34,493] Trial 19 finished with value: -299.419671369413 and parameters: {'embedding_dim': 353, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 16 with value: -33.283180595619186.
+[I 2025-12-17 23:15:23,618] Trial 20 finished with value: -351.42690822642317 and parameters: {'embedding_dim': 280, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 16 with value: -33.283180595619186.
+[I 2025-12-17 23:15:58,847] Trial 21 finished with value: -386.7006744229743 and parameters: {'embedding_dim': 128, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 16 with value: -33.283180595619186.
+[I 2025-12-17 23:16:45,704] Trial 22 finished with value: -239.78280340019978 and parameters: {'embedding_dim': 177, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 16 with value: -33.283180595619186.
+[I 2025-12-17 23:17:20,282] Trial 23 finished with value: -0.2927446973492319 and parameters: {'embedding_dim': 204, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 23 with value: -0.2927446973492319.
+[I 2025-12-17 23:17:43,671] Trial 24 finished with value: -5152.9789948015705 and parameters: {'embedding_dim': 210, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 23 with value: -0.2927446973492319.
+[I 2025-12-17 23:18:30,247] Trial 25 finished with value: -63.6747387029867 and parameters: {'embedding_dim': 222, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 23 with value: -0.2927446973492319.
+[I 2025-12-17 23:19:05,956] Trial 26 finished with value: -419.52417301265325 and parameters: {'embedding_dim': 273, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 23 with value: -0.2927446973492319.
+[I 2025-12-17 23:19:41,084] Trial 27 finished with value: -182.0743744769464 and parameters: {'embedding_dim': 176, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 23 with value: -0.2927446973492319.
+[I 2025-12-17 23:20:04,522] Trial 28 finished with value: -6067.593280200038 and parameters: {'embedding_dim': 317, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 23 with value: -0.2927446973492319.
+[I 2025-12-17 23:20:50,731] Trial 29 finished with value: -345.6266349150485 and parameters: {'embedding_dim': 195, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 23 with value: -0.2927446973492319.
+[I 2025-12-17 23:21:26,074] A new study created in memory with name: no-name-ec7eaeed-ecd0-4b97-a453-30bc21bf02ee
+[I 2025-12-17 23:21:32,696] Trial 0 finished with value: -116.38819007952519 and parameters: {'embedding_dim': 94, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -116.38819007952519.
+[I 2025-12-17 23:21:39,493] Trial 1 finished with value: -67.29495296955692 and parameters: {'embedding_dim': 112, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 1 with value: -67.29495296955692.
+[I 2025-12-17 23:21:43,015] Trial 2 finished with value: -34.69443742376649 and parameters: {'embedding_dim': 71, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -34.69443742376649.
+[I 2025-12-17 23:21:46,265] Trial 3 finished with value: -9.605959266479122 and parameters: {'embedding_dim': 122, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 3 with value: -9.605959266479122.
+[I 2025-12-17 23:21:49,536] Trial 4 finished with value: -163.36435886730857 and parameters: {'embedding_dim': 70, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 3 with value: -9.605959266479122.
+[I 2025-12-17 23:21:56,112] Trial 5 finished with value: -116.59918058611494 and parameters: {'embedding_dim': 99, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 3 with value: -9.605959266479122.
+[I 2025-12-17 23:22:01,226] Trial 6 finished with value: -191.4817345841124 and parameters: {'embedding_dim': 67, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 3 with value: -9.605959266479122.
+[I 2025-12-17 23:22:04,485] Trial 7 finished with value: -165.54167576763015 and parameters: {'embedding_dim': 91, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 3 with value: -9.605959266479122.
+[I 2025-12-17 23:22:07,876] Trial 8 finished with value: -42.677729608665395 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 3 with value: -9.605959266479122.
+[I 2025-12-17 23:22:11,304] Trial 9 finished with value: -72.52942197964936 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 3 with value: -9.605959266479122.
+[I 2025-12-17 23:22:16,757] Trial 10 finished with value: -58.13908526056764 and parameters: {'embedding_dim': 128, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 3 with value: -9.605959266479122.
+[I 2025-12-17 23:22:22,164] Trial 11 finished with value: -1.876723804784926 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:22:27,570] Trial 12 finished with value: -43.69750888732703 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:22:33,067] Trial 13 finished with value: -59.824191901638045 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:22:38,061] Trial 14 finished with value: -120.4024820176626 and parameters: {'embedding_dim': 84, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:22:41,653] Trial 15 finished with value: -67.45879535938806 and parameters: {'embedding_dim': 119, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:22:48,944] Trial 16 finished with value: -43.76971210886219 and parameters: {'embedding_dim': 79, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:22:53,943] Trial 17 finished with value: -84.51666484756272 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:22:59,353] Trial 18 finished with value: -27.61027059672154 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:23:02,690] Trial 19 finished with value: -43.5994761004549 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:23:08,136] Trial 20 finished with value: -30.50764947996504 and parameters: {'embedding_dim': 117, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:23:13,564] Trial 21 finished with value: -186.6965919325883 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:23:18,980] Trial 22 finished with value: -60.69353983997966 and parameters: {'embedding_dim': 85, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:23:26,272] Trial 23 finished with value: -49.874902561477036 and parameters: {'embedding_dim': 103, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:23:31,671] Trial 24 finished with value: -15.072717570181263 and parameters: {'embedding_dim': 76, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:23:34,946] Trial 25 finished with value: -113.65532394761348 and parameters: {'embedding_dim': 74, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:23:40,408] Trial 26 finished with value: -137.86209968374163 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:23:47,744] Trial 27 finished with value: -40.90543481629682 and parameters: {'embedding_dim': 66, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:23:51,098] Trial 28 finished with value: -41.57630166852792 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:23:57,680] Trial 29 finished with value: -11.257813099994108 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:24:04,259] Trial 30 finished with value: -48.38834259393369 and parameters: {'embedding_dim': 95, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:24:10,862] Trial 31 finished with value: -160.92691525753736 and parameters: {'embedding_dim': 121, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:24:15,799] Trial 32 finished with value: -83.59121698598679 and parameters: {'embedding_dim': 107, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:24:22,393] Trial 33 finished with value: -30.36187892797274 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:24:27,302] Trial 34 finished with value: -203.509983421825 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:24:33,898] Trial 35 finished with value: -175.21826237005246 and parameters: {'embedding_dim': 77, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:24:38,982] Trial 36 finished with value: -14.387112619265134 and parameters: {'embedding_dim': 70, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:24:42,349] Trial 37 finished with value: -57.05324503951645 and parameters: {'embedding_dim': 69, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:24:49,190] Trial 38 finished with value: -46.92668312585536 and parameters: {'embedding_dim': 71, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:24:52,551] Trial 39 finished with value: -123.21120547258423 and parameters: {'embedding_dim': 97, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:24:57,679] Trial 40 finished with value: -89.83102199899086 and parameters: {'embedding_dim': 123, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:25:02,788] Trial 41 finished with value: -6.114556326102898 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:25:07,857] Trial 42 finished with value: -14.044790630814154 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:25:12,970] Trial 43 finished with value: -93.86675008270737 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:25:18,041] Trial 44 finished with value: -64.58527035754081 and parameters: {'embedding_dim': 113, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:25:23,121] Trial 45 finished with value: -41.85274702973067 and parameters: {'embedding_dim': 88, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:25:26,470] Trial 46 finished with value: -206.2444983373873 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:25:31,492] Trial 47 finished with value: -42.69551596247405 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:25:38,497] Trial 48 finished with value: -12.674683767389778 and parameters: {'embedding_dim': 100, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:25:45,053] Trial 49 finished with value: -20.09720879698202 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 11 with value: -1.876723804784926.
+[I 2025-12-17 23:25:50,593] A new study created in memory with name: no-name-6cc9daf1-306a-4652-b45e-1480e378829f
+[I 2025-12-17 23:26:29,652] Trial 0 finished with value: -1872.9840036734458 and parameters: {'embedding_dim': 199, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 0 with value: -1872.9840036734458.
+[I 2025-12-17 23:27:00,641] Trial 1 finished with value: -661.6619920621176 and parameters: {'embedding_dim': 329, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -661.6619920621176.
+[I 2025-12-17 23:27:46,855] Trial 2 finished with value: -2411.411287965754 and parameters: {'embedding_dim': 509, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 1 with value: -661.6619920621176.
+[I 2025-12-17 23:28:11,273] Trial 3 finished with value: -833.2481813709578 and parameters: {'embedding_dim': 308, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 1 with value: -661.6619920621176.
+[I 2025-12-17 23:28:49,906] Trial 4 finished with value: -2284.4427374382103 and parameters: {'embedding_dim': 337, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 1 with value: -661.6619920621176.
+[I 2025-12-17 23:29:03,436] Trial 5 finished with value: -1260.5573424572376 and parameters: {'embedding_dim': 228, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 1 with value: -661.6619920621176.
+[I 2025-12-17 23:29:13,854] Trial 6 finished with value: -163.19817963605692 and parameters: {'embedding_dim': 342, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 6 with value: -163.19817963605692.
+[I 2025-12-17 23:30:00,371] Trial 7 finished with value: -971.1403589428919 and parameters: {'embedding_dim': 148, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 6 with value: -163.19817963605692.
+[I 2025-12-17 23:30:14,100] Trial 8 finished with value: -1293.7307222507904 and parameters: {'embedding_dim': 426, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 6 with value: -163.19817963605692.
+[I 2025-12-17 23:30:30,915] Trial 9 finished with value: -1121.7443489599486 and parameters: {'embedding_dim': 275, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 6 with value: -163.19817963605692.
+[I 2025-12-17 23:30:41,052] Trial 10 finished with value: -12044.293975179004 and parameters: {'embedding_dim': 435, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 6 with value: -163.19817963605692.
+[I 2025-12-17 23:30:52,121] Trial 11 finished with value: -895.2946799964827 and parameters: {'embedding_dim': 370, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 6 with value: -163.19817963605692.
+[I 2025-12-17 23:31:07,784] Trial 12 finished with value: -594.4291807405401 and parameters: {'embedding_dim': 399, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 6 with value: -163.19817963605692.
+[I 2025-12-17 23:31:23,534] Trial 13 finished with value: -3626.227648977171 and parameters: {'embedding_dim': 405, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 6 with value: -163.19817963605692.
+[I 2025-12-17 23:31:38,247] Trial 14 finished with value: -5184.282813222322 and parameters: {'embedding_dim': 490, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 6 with value: -163.19817963605692.
+[I 2025-12-17 23:31:52,835] Trial 15 finished with value: -2851.158510726543 and parameters: {'embedding_dim': 375, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 6 with value: -163.19817963605692.
+[I 2025-12-17 23:32:02,957] Trial 16 finished with value: -3809.342989804566 and parameters: {'embedding_dim': 274, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 6 with value: -163.19817963605692.
+[I 2025-12-17 23:32:18,224] Trial 17 finished with value: -1338.9647297179458 and parameters: {'embedding_dim': 457, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 6 with value: -163.19817963605692.
+[I 2025-12-17 23:32:29,034] Trial 18 finished with value: -712.3770642235679 and parameters: {'embedding_dim': 388, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 6 with value: -163.19817963605692.
+[I 2025-12-17 23:32:44,228] Trial 19 finished with value: -480.06352943647346 and parameters: {'embedding_dim': 281, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 6 with value: -163.19817963605692.
+[I 2025-12-17 23:32:51,920] Trial 20 finished with value: -3560.78143584878 and parameters: {'embedding_dim': 233, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 6 with value: -163.19817963605692.
+[I 2025-12-17 23:33:07,126] Trial 21 finished with value: -900.899335657276 and parameters: {'embedding_dim': 293, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 6 with value: -163.19817963605692.
+[I 2025-12-17 23:33:21,660] Trial 22 finished with value: -1712.0166125091703 and parameters: {'embedding_dim': 352, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 6 with value: -163.19817963605692.
+[I 2025-12-17 23:33:36,685] Trial 23 finished with value: -133.21506263566062 and parameters: {'embedding_dim': 245, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 23 with value: -133.21506263566062.
+[I 2025-12-17 23:33:47,460] Trial 24 finished with value: -5016.658293464539 and parameters: {'embedding_dim': 236, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 23 with value: -133.21506263566062.
+[I 2025-12-17 23:34:06,553] Trial 25 finished with value: -452.64954107923865 and parameters: {'embedding_dim': 173, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 23 with value: -133.21506263566062.
+[I 2025-12-17 23:34:26,170] Trial 26 finished with value: -836.8969659719131 and parameters: {'embedding_dim': 143, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 23 with value: -133.21506263566062.
+[I 2025-12-17 23:34:46,364] Trial 27 finished with value: -933.5752392014539 and parameters: {'embedding_dim': 178, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 23 with value: -133.21506263566062.
+[I 2025-12-17 23:34:59,426] Trial 28 finished with value: -2893.7077093599028 and parameters: {'embedding_dim': 183, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 23 with value: -133.21506263566062.
+[I 2025-12-17 23:35:09,118] Trial 29 finished with value: -1868.7490925038853 and parameters: {'embedding_dim': 252, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 23 with value: -133.21506263566062.
+[I 2025-12-17 23:35:25,364] A new study created in memory with name: no-name-246e9a40-9847-473a-bb72-08e0e6c9f2cd
+[I 2025-12-17 23:35:32,077] Trial 0 finished with value: -118.8897990512182 and parameters: {'embedding_dim': 71, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -118.8897990512182.
+[I 2025-12-17 23:35:37,064] Trial 1 finished with value: -120.48485503702256 and parameters: {'embedding_dim': 119, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -118.8897990512182.
+[I 2025-12-17 23:35:40,245] Trial 2 finished with value: -227.32355571423307 and parameters: {'embedding_dim': 107, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -118.8897990512182.
+[I 2025-12-17 23:35:43,543] Trial 3 finished with value: -126.33637419708337 and parameters: {'embedding_dim': 88, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 0 with value: -118.8897990512182.
+[I 2025-12-17 23:35:50,727] Trial 4 finished with value: -135.22483401889642 and parameters: {'embedding_dim': 90, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -118.8897990512182.
+[I 2025-12-17 23:35:56,003] Trial 5 finished with value: -77.39439261280631 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -77.39439261280631.
+[I 2025-12-17 23:36:03,285] Trial 6 finished with value: -75.75799812812033 and parameters: {'embedding_dim': 69, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 6 with value: -75.75799812812033.
+[I 2025-12-17 23:36:08,090] Trial 7 finished with value: -412.72670720214455 and parameters: {'embedding_dim': 113, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 6 with value: -75.75799812812033.
+[I 2025-12-17 23:36:11,246] Trial 8 finished with value: -232.74243937538148 and parameters: {'embedding_dim': 113, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 6 with value: -75.75799812812033.
+[I 2025-12-17 23:36:14,414] Trial 9 finished with value: -126.10963289322024 and parameters: {'embedding_dim': 128, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 6 with value: -75.75799812812033.
+[I 2025-12-17 23:36:21,674] Trial 10 finished with value: -150.8798974560368 and parameters: {'embedding_dim': 65, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 6 with value: -75.75799812812033.
+[I 2025-12-17 23:36:26,982] Trial 11 finished with value: -80.4683461048293 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 6 with value: -75.75799812812033.
+[I 2025-12-17 23:36:34,165] Trial 12 finished with value: -104.21753351876907 and parameters: {'embedding_dim': 80, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 6 with value: -75.75799812812033.
+[I 2025-12-17 23:36:39,498] Trial 13 finished with value: -204.99637943602315 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 6 with value: -75.75799812812033.
+[I 2025-12-17 23:36:44,898] Trial 14 finished with value: -249.9724895987023 and parameters: {'embedding_dim': 75, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 6 with value: -75.75799812812033.
+[I 2025-12-17 23:36:52,248] Trial 15 finished with value: -118.09020304807201 and parameters: {'embedding_dim': 66, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 6 with value: -75.75799812812033.
+[I 2025-12-17 23:36:57,540] Trial 16 finished with value: -170.95965263591432 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 6 with value: -75.75799812812033.
+[I 2025-12-17 23:37:04,719] Trial 17 finished with value: -262.35200516693146 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 6 with value: -75.75799812812033.
+[I 2025-12-17 23:37:10,018] Trial 18 finished with value: -17.348062808302057 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:37:15,028] Trial 19 finished with value: -201.14059654803623 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:37:22,238] Trial 20 finished with value: -351.7212606798153 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:37:27,547] Trial 21 finished with value: -159.11269643914372 and parameters: {'embedding_dim': 81, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:37:32,944] Trial 22 finished with value: -107.71994602625077 and parameters: {'embedding_dim': 71, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:37:38,329] Trial 23 finished with value: -145.87633909026965 and parameters: {'embedding_dim': 94, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:37:41,745] Trial 24 finished with value: -196.26993377681652 and parameters: {'embedding_dim': 83, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:37:47,056] Trial 25 finished with value: -85.53095164236322 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:37:52,341] Trial 26 finished with value: -93.83032377025093 and parameters: {'embedding_dim': 70, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:37:59,504] Trial 27 finished with value: -165.13498305106444 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:38:04,435] Trial 28 finished with value: -284.49722902226006 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:38:10,883] Trial 29 finished with value: -48.13195075239872 and parameters: {'embedding_dim': 68, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:38:17,371] Trial 30 finished with value: -138.614215500121 and parameters: {'embedding_dim': 69, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:38:23,829] Trial 31 finished with value: -254.07580967923445 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:38:31,709] Trial 32 finished with value: -52.223318991139315 and parameters: {'embedding_dim': 68, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:38:38,172] Trial 33 finished with value: -148.95798263952884 and parameters: {'embedding_dim': 68, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:38:44,649] Trial 34 finished with value: -109.72047694861313 and parameters: {'embedding_dim': 67, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:38:51,113] Trial 35 finished with value: -105.15934800674587 and parameters: {'embedding_dim': 72, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:38:57,588] Trial 36 finished with value: -209.9747926976041 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:39:04,291] Trial 37 finished with value: -275.0291735692386 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:39:10,760] Trial 38 finished with value: -79.43047964836528 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:39:17,218] Trial 39 finished with value: -103.31604242852154 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:39:23,665] Trial 40 finished with value: -529.7354356966677 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:39:31,278] Trial 41 finished with value: -58.672200680085794 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:39:34,592] Trial 42 finished with value: -123.67647877045613 and parameters: {'embedding_dim': 69, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:39:39,595] Trial 43 finished with value: -338.4173957279085 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:39:44,623] Trial 44 finished with value: -131.12098281310665 and parameters: {'embedding_dim': 68, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:39:49,617] Trial 45 finished with value: -140.32444070576616 and parameters: {'embedding_dim': 126, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:39:52,796] Trial 46 finished with value: -80.1567671492928 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:39:59,520] Trial 47 finished with value: -187.23164623922827 and parameters: {'embedding_dim': 72, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:40:05,277] Trial 48 finished with value: -121.71537105843476 and parameters: {'embedding_dim': 65, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:40:11,277] Trial 49 finished with value: -385.12672364522905 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 18 with value: -17.348062808302057.
+[I 2025-12-17 23:40:17,167] A new study created in memory with name: no-name-8166f8fc-4775-47ec-8a84-491b58b86ab4
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_10000_3_seoul_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_10000_3_seoul_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan10000_3_seoul.csv: Class 0=8007 | Class 1=9848
+Saved ../../data/data_oversampled/ctgan10000/ctgan10000_3_seoul.csv: Class 0=8007 | Class 1=9848 | Class 2=15873
+Processing ../../data/data_for_modeling/busan_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/busan_train.csv: Optimizing CTGAN for class 1...
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_10000_3_busan_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_10000_3_busan_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan10000_3_busan.csv: Class 0=9604 | Class 1=8626
+Saved ../../data/data_oversampled/ctgan10000/ctgan10000_3_busan.csv: Class 0=9604 | Class 1=8626 | Class 2=16439
+Processing ../../data/data_for_modeling/daegu_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/daegu_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-17 23:40:35,034] Trial 0 finished with value: -454.7782534982109 and parameters: {'embedding_dim': 256, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -454.7782534982109.
+[I 2025-12-17 23:40:44,100] Trial 1 finished with value: -887.1946950929678 and parameters: {'embedding_dim': 305, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 0 with value: -454.7782534982109.
+[I 2025-12-17 23:40:54,989] Trial 2 finished with value: -937.9884276606135 and parameters: {'embedding_dim': 292, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 0 with value: -454.7782534982109.
+[I 2025-12-17 23:41:06,162] Trial 3 finished with value: -402.2463699961404 and parameters: {'embedding_dim': 379, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 3 with value: -402.2463699961404.
+[I 2025-12-17 23:41:17,247] Trial 4 finished with value: -298.5611940850258 and parameters: {'embedding_dim': 261, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -298.5611940850258.
+[I 2025-12-17 23:41:28,157] Trial 5 finished with value: -172.94506595175454 and parameters: {'embedding_dim': 376, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 5 with value: -172.94506595175454.
+[I 2025-12-17 23:41:41,346] Trial 6 finished with value: -319.2964180445853 and parameters: {'embedding_dim': 273, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 5 with value: -172.94506595175454.
+[I 2025-12-17 23:41:59,346] Trial 7 finished with value: -346.29795912041925 and parameters: {'embedding_dim': 194, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 5 with value: -172.94506595175454.
+[I 2025-12-17 23:42:20,322] Trial 8 finished with value: -160.0948417581489 and parameters: {'embedding_dim': 412, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 8 with value: -160.0948417581489.
+[I 2025-12-17 23:42:35,974] Trial 9 finished with value: -265.54686393833754 and parameters: {'embedding_dim': 320, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 8 with value: -160.0948417581489.
+[I 2025-12-17 23:42:43,627] Trial 10 finished with value: -591.9789590737862 and parameters: {'embedding_dim': 498, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 8 with value: -160.0948417581489.
+[I 2025-12-17 23:42:58,763] Trial 11 finished with value: -384.47417464887735 and parameters: {'embedding_dim': 422, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 8 with value: -160.0948417581489.
+[I 2025-12-17 23:43:08,471] Trial 12 finished with value: -493.3867898380204 and parameters: {'embedding_dim': 407, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 8 with value: -160.0948417581489.
+[I 2025-12-17 23:43:19,802] Trial 13 finished with value: -206.31586695770565 and parameters: {'embedding_dim': 481, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 8 with value: -160.0948417581489.
+[I 2025-12-17 23:43:33,865] Trial 14 finished with value: -205.08197090514335 and parameters: {'embedding_dim': 360, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 8 with value: -160.0948417581489.
+[I 2025-12-17 23:43:58,791] Trial 15 finished with value: -97.86468416273541 and parameters: {'embedding_dim': 446, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 15 with value: -97.86468416273541.
+[I 2025-12-17 23:44:21,495] Trial 16 finished with value: -188.37593181700404 and parameters: {'embedding_dim': 457, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 15 with value: -97.86468416273541.
+[I 2025-12-17 23:44:44,136] Trial 17 finished with value: -371.24538369390586 and parameters: {'embedding_dim': 437, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 15 with value: -97.86468416273541.
+[I 2025-12-17 23:45:04,208] Trial 18 finished with value: -632.7164271828979 and parameters: {'embedding_dim': 350, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 15 with value: -97.86468416273541.
+[I 2025-12-17 23:45:28,664] Trial 19 finished with value: -453.9207072707553 and parameters: {'embedding_dim': 508, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 15 with value: -97.86468416273541.
+[I 2025-12-17 23:45:48,385] Trial 20 finished with value: -132.07644948986467 and parameters: {'embedding_dim': 459, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 15 with value: -97.86468416273541.
+[I 2025-12-17 23:46:09,972] Trial 21 finished with value: -93.42906564008038 and parameters: {'embedding_dim': 453, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 21 with value: -93.42906564008038.
+[I 2025-12-17 23:46:34,998] Trial 22 finished with value: -447.3929487456783 and parameters: {'embedding_dim': 463, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 21 with value: -93.42906564008038.
+[I 2025-12-17 23:46:54,090] Trial 23 finished with value: -270.56195698658416 and parameters: {'embedding_dim': 130, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 21 with value: -93.42906564008038.
+[I 2025-12-17 23:47:14,686] Trial 24 finished with value: -408.00085891276774 and parameters: {'embedding_dim': 452, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 21 with value: -93.42906564008038.
+[I 2025-12-17 23:47:37,682] Trial 25 finished with value: -418.1775417499736 and parameters: {'embedding_dim': 397, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 21 with value: -93.42906564008038.
+[I 2025-12-17 23:47:54,594] Trial 26 finished with value: -874.0793273480747 and parameters: {'embedding_dim': 480, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 21 with value: -93.42906564008038.
+[I 2025-12-17 23:48:13,800] Trial 27 finished with value: -487.77455953975306 and parameters: {'embedding_dim': 343, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 21 with value: -93.42906564008038.
+[I 2025-12-17 23:48:39,954] Trial 28 finished with value: -189.0432981302802 and parameters: {'embedding_dim': 511, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 21 with value: -93.42906564008038.
+[I 2025-12-17 23:48:57,393] Trial 29 finished with value: -230.82290315625784 and parameters: {'embedding_dim': 431, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 21 with value: -93.42906564008038.
+[I 2025-12-17 23:49:19,006] A new study created in memory with name: no-name-d32b4c3f-c20f-48c3-8f36-dd493fa2b907
+[I 2025-12-17 23:49:22,782] Trial 0 finished with value: -33.6089444063855 and parameters: {'embedding_dim': 66, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -33.6089444063855.
+[I 2025-12-17 23:49:29,317] Trial 1 finished with value: -26.167599457706434 and parameters: {'embedding_dim': 109, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 1 with value: -26.167599457706434.
+[I 2025-12-17 23:49:34,804] Trial 2 finished with value: -20.218601453148473 and parameters: {'embedding_dim': 70, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -20.218601453148473.
+[I 2025-12-17 23:49:42,157] Trial 3 finished with value: -148.5891575168304 and parameters: {'embedding_dim': 67, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -20.218601453148473.
+[I 2025-12-17 23:49:46,522] Trial 4 finished with value: -11.9030830304244 and parameters: {'embedding_dim': 122, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 4 with value: -11.9030830304244.
+[I 2025-12-17 23:49:51,498] Trial 5 finished with value: -114.72372625560705 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 4 with value: -11.9030830304244.
+[I 2025-12-17 23:49:58,171] Trial 6 finished with value: -33.74899233403135 and parameters: {'embedding_dim': 113, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 4 with value: -11.9030830304244.
+[I 2025-12-17 23:50:03,318] Trial 7 finished with value: -119.80207755300614 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -11.9030830304244.
+[I 2025-12-17 23:50:06,884] Trial 8 finished with value: -256.37582428046863 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 4 with value: -11.9030830304244.
+[I 2025-12-17 23:50:10,305] Trial 9 finished with value: -34.67928375729797 and parameters: {'embedding_dim': 117, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 4 with value: -11.9030830304244.
+[I 2025-12-17 23:50:13,656] Trial 10 finished with value: -101.54891106618074 and parameters: {'embedding_dim': 85, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 4 with value: -11.9030830304244.
+[I 2025-12-17 23:50:20,815] Trial 11 finished with value: -184.4717214261836 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -11.9030830304244.
+[I 2025-12-17 23:50:25,849] Trial 12 finished with value: -89.75932965594048 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 4 with value: -11.9030830304244.
+[I 2025-12-17 23:50:33,416] Trial 13 finished with value: -32.46105785490658 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -11.9030830304244.
+[I 2025-12-17 23:50:38,694] Trial 14 finished with value: -12.25709191886507 and parameters: {'embedding_dim': 100, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -11.9030830304244.
+[I 2025-12-17 23:50:42,116] Trial 15 finished with value: -57.20843759505806 and parameters: {'embedding_dim': 103, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 4 with value: -11.9030830304244.
+[I 2025-12-17 23:50:49,713] Trial 16 finished with value: -14.372934182247286 and parameters: {'embedding_dim': 121, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 4 with value: -11.9030830304244.
+[I 2025-12-17 23:50:56,606] Trial 17 finished with value: -14.604505320072104 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -11.9030830304244.
+[I 2025-12-17 23:51:00,206] Trial 18 finished with value: -58.65057830457546 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 4 with value: -11.9030830304244.
+[I 2025-12-17 23:51:05,202] Trial 19 finished with value: -70.81773191400124 and parameters: {'embedding_dim': 121, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 4 with value: -11.9030830304244.
+[I 2025-12-17 23:51:12,198] Trial 20 finished with value: -101.06482703321079 and parameters: {'embedding_dim': 109, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 4 with value: -11.9030830304244.
+[I 2025-12-17 23:51:21,247] Trial 21 finished with value: -30.47879858416917 and parameters: {'embedding_dim': 122, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 4 with value: -11.9030830304244.
+[I 2025-12-17 23:51:28,253] Trial 22 finished with value: -58.703394679902246 and parameters: {'embedding_dim': 121, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 4 with value: -11.9030830304244.
+[I 2025-12-17 23:51:35,317] Trial 23 finished with value: -55.27734593054603 and parameters: {'embedding_dim': 113, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 4 with value: -11.9030830304244.
+[I 2025-12-17 23:51:40,666] Trial 24 finished with value: -7.898449281789813 and parameters: {'embedding_dim': 105, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:51:47,717] Trial 25 finished with value: -62.550489530141846 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:51:53,049] Trial 26 finished with value: -67.47972326472622 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:51:58,064] Trial 27 finished with value: -41.218053146233544 and parameters: {'embedding_dim': 107, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:52:01,489] Trial 28 finished with value: -527.722178747544 and parameters: {'embedding_dim': 90, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:52:04,799] Trial 29 finished with value: -539.9345505471055 and parameters: {'embedding_dim': 99, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:52:09,959] Trial 30 finished with value: -75.51551142494661 and parameters: {'embedding_dim': 115, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:52:16,854] Trial 31 finished with value: -59.190637376133054 and parameters: {'embedding_dim': 123, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:52:22,582] Trial 32 finished with value: -96.14054248114635 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:52:30,816] Trial 33 finished with value: -42.353261744083675 and parameters: {'embedding_dim': 117, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:52:36,012] Trial 34 finished with value: -89.95617195343955 and parameters: {'embedding_dim': 110, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:52:39,326] Trial 35 finished with value: -112.54743257617012 and parameters: {'embedding_dim': 124, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:52:44,885] Trial 36 finished with value: -71.78544603331059 and parameters: {'embedding_dim': 113, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:52:50,051] Trial 37 finished with value: -150.85292437494255 and parameters: {'embedding_dim': 118, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:52:55,022] Trial 38 finished with value: -19.663989674724785 and parameters: {'embedding_dim': 97, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:53:04,361] Trial 39 finished with value: -238.65736722879663 and parameters: {'embedding_dim': 125, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:53:08,071] Trial 40 finished with value: -17.278241469130904 and parameters: {'embedding_dim': 111, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:53:13,240] Trial 41 finished with value: -33.477531034468015 and parameters: {'embedding_dim': 94, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:53:18,354] Trial 42 finished with value: -159.90401134183082 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:53:23,522] Trial 43 finished with value: -34.37920057979933 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:53:28,695] Trial 44 finished with value: -59.2120235959125 and parameters: {'embedding_dim': 86, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:53:32,100] Trial 45 finished with value: -115.29873187352047 and parameters: {'embedding_dim': 84, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:53:37,104] Trial 46 finished with value: -84.04008984188707 and parameters: {'embedding_dim': 105, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:53:42,693] Trial 47 finished with value: -107.74934652860505 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:53:51,087] Trial 48 finished with value: -46.48003667142175 and parameters: {'embedding_dim': 94, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:53:56,022] Trial 49 finished with value: -161.11957976596437 and parameters: {'embedding_dim': 88, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 24 with value: -7.898449281789813.
+[I 2025-12-17 23:54:02,044] A new study created in memory with name: no-name-2297916b-e085-4291-8493-dad6cc5ab58b
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_10000_3_daegu_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_10000_3_daegu_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan10000_3_daegu.csv: Class 0=8868 | Class 1=9275
+Saved ../../data/data_oversampled/ctgan10000/ctgan10000_3_daegu.csv: Class 0=8868 | Class 1=9275 | Class 2=16913
+Processing ../../data/data_for_modeling/daejeon_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/daejeon_train.csv: Optimizing CTGAN for class 1...
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-17 23:54:23,351] Trial 0 finished with value: -588.1569418328693 and parameters: {'embedding_dim': 392, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 0 with value: -588.1569418328693.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-17 23:54:47,208] Trial 1 finished with value: -3088.2426162734505 and parameters: {'embedding_dim': 144, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 0 with value: -588.1569418328693.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-17 23:55:09,811] Trial 2 finished with value: -5152.508400612565 and parameters: {'embedding_dim': 178, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 0 with value: -588.1569418328693.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-17 23:55:30,416] Trial 3 finished with value: -458.0122704231919 and parameters: {'embedding_dim': 287, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 3 with value: -458.0122704231919.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-17 23:56:08,083] Trial 4 finished with value: -132.32149710605532 and parameters: {'embedding_dim': 137, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 4 with value: -132.32149710605532.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-17 23:56:55,859] Trial 5 finished with value: -756.5147855758802 and parameters: {'embedding_dim': 306, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -132.32149710605532.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-17 23:57:07,538] Trial 6 finished with value: -545.0067051833599 and parameters: {'embedding_dim': 177, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 4 with value: -132.32149710605532.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-17 23:57:16,513] Trial 7 finished with value: -668.4376625124135 and parameters: {'embedding_dim': 500, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 4 with value: -132.32149710605532.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-17 23:57:30,745] Trial 8 finished with value: -432.73162538543005 and parameters: {'embedding_dim': 352, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 4 with value: -132.32149710605532.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-17 23:58:15,448] Trial 9 finished with value: -3237.0060538904827 and parameters: {'embedding_dim': 294, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 4 with value: -132.32149710605532.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-17 23:59:13,374] Trial 10 finished with value: -103.66311694826244 and parameters: {'embedding_dim': 227, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 10 with value: -103.66311694826244.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:00:10,990] Trial 11 finished with value: -202.02105662162086 and parameters: {'embedding_dim': 227, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 10 with value: -103.66311694826244.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:01:09,677] Trial 12 finished with value: -271.12107472218645 and parameters: {'embedding_dim': 231, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 10 with value: -103.66311694826244.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:02:07,918] Trial 13 finished with value: -779.9421757065929 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 10 with value: -103.66311694826244.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:02:49,613] Trial 14 finished with value: -504.1139105394466 and parameters: {'embedding_dim': 222, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 10 with value: -103.66311694826244.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:03:53,643] Trial 15 finished with value: -694.6962245547178 and parameters: {'embedding_dim': 193, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 10 with value: -103.66311694826244.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:04:34,885] Trial 16 finished with value: -445.7191529570693 and parameters: {'embedding_dim': 246, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 10 with value: -103.66311694826244.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:05:47,253] Trial 17 finished with value: -996.7815579243434 and parameters: {'embedding_dim': 402, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 10 with value: -103.66311694826244.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:06:22,833] Trial 18 finished with value: -165.07203881826368 and parameters: {'embedding_dim': 161, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 10 with value: -103.66311694826244.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:07:08,583] Trial 19 finished with value: -46.8616102267589 and parameters: {'embedding_dim': 273, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 19 with value: -46.8616102267589.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:07:32,338] Trial 20 finished with value: -821.7228815687399 and parameters: {'embedding_dim': 265, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 19 with value: -46.8616102267589.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:08:18,785] Trial 21 finished with value: -281.7871594167929 and parameters: {'embedding_dim': 204, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 19 with value: -46.8616102267589.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:09:04,992] Trial 22 finished with value: -95.08700030547638 and parameters: {'embedding_dim': 358, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 19 with value: -46.8616102267589.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:09:39,697] Trial 23 finished with value: -627.8326831572796 and parameters: {'embedding_dim': 346, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 19 with value: -46.8616102267589.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:10:25,870] Trial 24 finished with value: -64.09347838743875 and parameters: {'embedding_dim': 449, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 19 with value: -46.8616102267589.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:11:12,144] Trial 25 finished with value: -604.1033890197558 and parameters: {'embedding_dim': 482, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 19 with value: -46.8616102267589.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:11:47,326] Trial 26 finished with value: -1442.1252317301014 and parameters: {'embedding_dim': 417, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 19 with value: -46.8616102267589.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:12:33,922] Trial 27 finished with value: -79.54400411182868 and parameters: {'embedding_dim': 456, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 19 with value: -46.8616102267589.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:13:20,541] Trial 28 finished with value: -207.64161135200214 and parameters: {'embedding_dim': 454, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 19 with value: -46.8616102267589.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:14:03,602] Trial 29 finished with value: -963.8947680269393 and parameters: {'embedding_dim': 454, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 19 with value: -46.8616102267589.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:15:04,975] A new study created in memory with name: no-name-cc6c2f65-9928-4280-8292-86c41945377c
+[I 2025-12-18 00:15:09,862] Trial 0 finished with value: -120.13252519371541 and parameters: {'embedding_dim': 94, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -120.13252519371541.
+[I 2025-12-18 00:15:14,999] Trial 1 finished with value: -387.51443489373196 and parameters: {'embedding_dim': 123, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -120.13252519371541.
+[I 2025-12-18 00:15:21,126] Trial 2 finished with value: -122.26695432559697 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -120.13252519371541.
+[I 2025-12-18 00:15:25,564] Trial 3 finished with value: -98.78517546999265 and parameters: {'embedding_dim': 65, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 3 with value: -98.78517546999265.
+[I 2025-12-18 00:15:32,611] Trial 4 finished with value: -81.3082233468624 and parameters: {'embedding_dim': 113, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 4 with value: -81.3082233468624.
+[I 2025-12-18 00:15:38,140] Trial 5 finished with value: -114.75996855209708 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -81.3082233468624.
+[I 2025-12-18 00:15:46,454] Trial 6 finished with value: -154.63048142796214 and parameters: {'embedding_dim': 125, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 4 with value: -81.3082233468624.
+[I 2025-12-18 00:15:49,987] Trial 7 finished with value: -367.1772413163528 and parameters: {'embedding_dim': 67, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 4 with value: -81.3082233468624.
+[I 2025-12-18 00:15:57,311] Trial 8 finished with value: -49.492474787028925 and parameters: {'embedding_dim': 87, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 8 with value: -49.492474787028925.
+[I 2025-12-18 00:16:03,479] Trial 9 finished with value: -64.19141549479195 and parameters: {'embedding_dim': 71, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 8 with value: -49.492474787028925.
+[I 2025-12-18 00:16:10,792] Trial 10 finished with value: -46.45158285961176 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 10 with value: -46.45158285961176.
+[I 2025-12-18 00:16:18,140] Trial 11 finished with value: -40.10716740415553 and parameters: {'embedding_dim': 83, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 11 with value: -40.10716740415553.
+[I 2025-12-18 00:16:25,424] Trial 12 finished with value: -40.373215684526166 and parameters: {'embedding_dim': 81, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 11 with value: -40.10716740415553.
+[I 2025-12-18 00:16:34,185] Trial 13 finished with value: -2.4022131036681262 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:16:43,002] Trial 14 finished with value: -72.39606522835777 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:16:49,486] Trial 15 finished with value: -3.525339500428452 and parameters: {'embedding_dim': 94, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:16:56,089] Trial 16 finished with value: -234.93027110460707 and parameters: {'embedding_dim': 100, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:16:59,338] Trial 17 finished with value: -97.69231653863226 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:17:04,275] Trial 18 finished with value: -22.696919157297273 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:17:11,042] Trial 19 finished with value: -47.56813858155212 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:17:19,196] Trial 20 finished with value: -55.17308670073707 and parameters: {'embedding_dim': 88, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:17:24,159] Trial 21 finished with value: -59.7100805924995 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:17:29,107] Trial 22 finished with value: -82.45763927864064 and parameters: {'embedding_dim': 105, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:17:35,092] Trial 23 finished with value: -27.7656390461443 and parameters: {'embedding_dim': 118, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:17:40,134] Trial 24 finished with value: -69.47224746960725 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:17:43,495] Trial 25 finished with value: -47.7584530060154 and parameters: {'embedding_dim': 115, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:17:51,402] Trial 26 finished with value: -121.9006857928344 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:17:56,314] Trial 27 finished with value: -6.144385493378417 and parameters: {'embedding_dim': 107, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:18:03,124] Trial 28 finished with value: -134.2889260059179 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:18:08,056] Trial 29 finished with value: -4.1246551105223315 and parameters: {'embedding_dim': 97, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:18:15,675] Trial 30 finished with value: -39.94848362088213 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:18:22,400] Trial 31 finished with value: -53.60487440077577 and parameters: {'embedding_dim': 97, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:18:27,353] Trial 32 finished with value: -73.84758797020271 and parameters: {'embedding_dim': 109, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:18:32,359] Trial 33 finished with value: -114.52750173478 and parameters: {'embedding_dim': 118, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:18:37,487] Trial 34 finished with value: -86.48404510041809 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:18:44,739] Trial 35 finished with value: -12.064478188904776 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:18:48,240] Trial 36 finished with value: -139.20471154626716 and parameters: {'embedding_dim': 109, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:18:53,186] Trial 37 finished with value: -97.16033571660438 and parameters: {'embedding_dim': 99, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:18:59,391] Trial 38 finished with value: -149.37988974780876 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:19:02,684] Trial 39 finished with value: -77.62806757543805 and parameters: {'embedding_dim': 123, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:19:08,651] Trial 40 finished with value: -28.418882135131984 and parameters: {'embedding_dim': 79, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:19:15,487] Trial 41 finished with value: -84.04760410341709 and parameters: {'embedding_dim': 104, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:19:20,748] Trial 42 finished with value: -80.93047508123331 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:19:25,857] Trial 43 finished with value: -99.50297296613783 and parameters: {'embedding_dim': 113, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:19:32,608] Trial 44 finished with value: -106.89987990618442 and parameters: {'embedding_dim': 68, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:19:39,452] Trial 45 finished with value: -278.09231130408654 and parameters: {'embedding_dim': 86, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:19:46,923] Trial 46 finished with value: -72.70258675468477 and parameters: {'embedding_dim': 72, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:19:52,007] Trial 47 finished with value: -26.7730921978807 and parameters: {'embedding_dim': 97, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:19:59,297] Trial 48 finished with value: -398.0867341081083 and parameters: {'embedding_dim': 109, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:20:05,265] Trial 49 finished with value: -30.353738899722067 and parameters: {'embedding_dim': 91, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 13 with value: -2.4022131036681262.
+[I 2025-12-18 00:20:14,550] A new study created in memory with name: no-name-a0a26834-7872-43ca-b90a-1d831d30283c
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_10000_3_daejeon_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_10000_3_daejeon_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan10000_3_daejeon.csv: Class 0=8841 | Class 1=9748
+Saved ../../data/data_oversampled/ctgan10000/ctgan10000_3_daejeon.csv: Class 0=8841 | Class 1=9748 | Class 2=15784
+Processing ../../data/data_for_modeling/gwangju_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/gwangju_train.csv: Optimizing CTGAN for class 1...
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:20:38,682] Trial 0 finished with value: -672.5185634499633 and parameters: {'embedding_dim': 160, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -672.5185634499633.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:20:54,795] Trial 1 finished with value: -243.5598097878859 and parameters: {'embedding_dim': 234, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 1 with value: -243.5598097878859.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:21:11,312] Trial 2 finished with value: -2872.5015734586505 and parameters: {'embedding_dim': 398, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 1 with value: -243.5598097878859.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:21:54,184] Trial 3 finished with value: -584.992187177288 and parameters: {'embedding_dim': 191, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -243.5598097878859.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:22:46,769] Trial 4 finished with value: -531.6715536725928 and parameters: {'embedding_dim': 384, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 1 with value: -243.5598097878859.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:23:01,047] Trial 5 finished with value: -195.0168372979536 and parameters: {'embedding_dim': 182, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:24:02,329] Trial 6 finished with value: -388.9017631102636 and parameters: {'embedding_dim': 465, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:25:13,002] Trial 7 finished with value: -1552.882683457334 and parameters: {'embedding_dim': 430, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:25:58,162] Trial 8 finished with value: -196.07067485957825 and parameters: {'embedding_dim': 420, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:26:47,196] Trial 9 finished with value: -1368.6376444136472 and parameters: {'embedding_dim': 449, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:26:58,687] Trial 10 finished with value: -2350.7327904076255 and parameters: {'embedding_dim': 268, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:27:09,723] Trial 11 finished with value: -1338.8940216320204 and parameters: {'embedding_dim': 315, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:27:26,114] Trial 12 finished with value: -2157.6373499181514 and parameters: {'embedding_dim': 331, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:27:38,549] Trial 13 finished with value: -2357.9819731238076 and parameters: {'embedding_dim': 492, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:27:50,145] Trial 14 finished with value: -2147.0206565221597 and parameters: {'embedding_dim': 129, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:28:15,070] Trial 15 finished with value: -612.002042961095 and parameters: {'embedding_dim': 341, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:28:23,123] Trial 16 finished with value: -1819.8861133784953 and parameters: {'embedding_dim': 261, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:28:51,836] Trial 17 finished with value: -3605.3454000531315 and parameters: {'embedding_dim': 510, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:29:05,312] Trial 18 finished with value: -511.0256352421825 and parameters: {'embedding_dim': 381, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:29:30,530] Trial 19 finished with value: -848.9688322820289 and parameters: {'embedding_dim': 209, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:29:42,316] Trial 20 finished with value: -2357.8787891032 and parameters: {'embedding_dim': 293, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:29:56,153] Trial 21 finished with value: -290.0442307289686 and parameters: {'embedding_dim': 224, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:30:09,871] Trial 22 finished with value: -406.5644132994663 and parameters: {'embedding_dim': 241, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:30:23,106] Trial 23 finished with value: -333.0538947851311 and parameters: {'embedding_dim': 167, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:30:39,350] Trial 24 finished with value: -272.38494916230354 and parameters: {'embedding_dim': 182, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:31:09,123] Trial 25 finished with value: -1208.0512589939149 and parameters: {'embedding_dim': 287, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:31:23,204] Trial 26 finished with value: -253.04472960217794 and parameters: {'embedding_dim': 149, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:31:37,164] Trial 27 finished with value: -920.9400466773875 and parameters: {'embedding_dim': 219, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:31:48,460] Trial 28 finished with value: -1522.314688506303 and parameters: {'embedding_dim': 348, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+[I 2025-12-18 00:32:18,394] Trial 29 finished with value: -2578.511417516971 and parameters: {'embedding_dim': 246, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -195.0168372979536.
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+/opt/conda/envs/py39/lib/python3.9/site-packages/sklearn/base.py:380: InconsistentVersionWarning: Trying to unpickle estimator BayesianGaussianMixture from version 1.3.0 when using version 1.6.1. This might lead to breaking code or invalid results. Use at your own risk. For more info please refer to:
+https://scikit-learn.org/stable/model_persistence.html#security-maintainability-limitations
+  warnings.warn(
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_10000_3_gwangju_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_10000_3_gwangju_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan10000_3_gwangju.csv: Class 0=8327 | Class 1=9255
+Saved ../../data/data_oversampled/ctgan10000/ctgan10000_3_gwangju.csv: Class 0=8327 | Class 1=9255 | Class 2=16144
+
+=== Processing 20000 samples ===
+Running ctgan_sample_20000_1.py...
+[I 2025-12-18 00:32:39,178] A new study created in memory with name: no-name-67cb4696-af53-4a40-a12a-880a7d814d51
+[I 2025-12-18 00:33:27,481] Trial 0 finished with value: -16.04973187567166 and parameters: {'embedding_dim': 125, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -16.04973187567166.
+[I 2025-12-18 00:33:38,861] Trial 1 finished with value: -55.00962030296798 and parameters: {'embedding_dim': 83, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -16.04973187567166.
+[I 2025-12-18 00:34:10,959] Trial 2 finished with value: -19.71493441999562 and parameters: {'embedding_dim': 113, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -16.04973187567166.
+[I 2025-12-18 00:34:33,882] Trial 3 finished with value: -3.3447741112988827 and parameters: {'embedding_dim': 66, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 3 with value: -3.3447741112988827.
+[I 2025-12-18 00:34:37,743] Trial 4 finished with value: -360.77624516634665 and parameters: {'embedding_dim': 87, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 3 with value: -3.3447741112988827.
+[I 2025-12-18 00:34:41,633] Trial 5 finished with value: -31.44717959249561 and parameters: {'embedding_dim': 121, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 3 with value: -3.3447741112988827.
+[I 2025-12-18 00:35:04,817] Trial 6 finished with value: -53.21177413068011 and parameters: {'embedding_dim': 109, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 3 with value: -3.3447741112988827.
+[I 2025-12-18 00:35:10,577] Trial 7 finished with value: -77.34954905841015 and parameters: {'embedding_dim': 80, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 3 with value: -3.3447741112988827.
+[I 2025-12-18 00:35:17,160] Trial 8 finished with value: -15.459290235756267 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 3 with value: -3.3447741112988827.
+[I 2025-12-18 00:35:23,755] Trial 9 finished with value: -9.724091011666493 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 3 with value: -3.3447741112988827.
+[I 2025-12-18 00:35:55,024] Trial 10 finished with value: -73.60480241836815 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 3 with value: -3.3447741112988827.
+[I 2025-12-18 00:36:01,574] Trial 11 finished with value: -82.75325302267883 and parameters: {'embedding_dim': 65, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 3 with value: -3.3447741112988827.
+[I 2025-12-18 00:36:11,475] Trial 12 finished with value: -1.545320811832459 and parameters: {'embedding_dim': 97, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 12 with value: -1.545320811832459.
+[I 2025-12-18 00:36:34,544] Trial 13 finished with value: -2.7734370813212132 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 12 with value: -1.545320811832459.
+[I 2025-12-18 00:36:44,561] Trial 14 finished with value: -5.48997342246492 and parameters: {'embedding_dim': 97, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 12 with value: -1.545320811832459.
+[I 2025-12-18 00:37:07,533] Trial 15 finished with value: -1.0200922953932452 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 15 with value: -1.0200922953932452.
+[I 2025-12-18 00:37:20,992] Trial 16 finished with value: -26.09185198286791 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 15 with value: -1.0200922953932452.
+[I 2025-12-18 00:37:30,967] Trial 17 finished with value: -1.179209883980152 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 15 with value: -1.0200922953932452.
+[I 2025-12-18 00:37:54,031] Trial 18 finished with value: -17.41269773176272 and parameters: {'embedding_dim': 90, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 15 with value: -1.0200922953932452.
+[I 2025-12-18 00:38:01,675] Trial 19 finished with value: -144.5287258278244 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -1.0200922953932452.
+[I 2025-12-18 00:38:11,724] Trial 20 finished with value: -4.7350679362727925 and parameters: {'embedding_dim': 105, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 15 with value: -1.0200922953932452.
+[I 2025-12-18 00:38:21,781] Trial 21 finished with value: -38.474833923941276 and parameters: {'embedding_dim': 99, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 15 with value: -1.0200922953932452.
+[I 2025-12-18 00:38:31,829] Trial 22 finished with value: -7.629129305590763 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 15 with value: -1.0200922953932452.
+[I 2025-12-18 00:38:41,870] Trial 23 finished with value: -81.19847781826584 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 15 with value: -1.0200922953932452.
+[I 2025-12-18 00:38:51,850] Trial 24 finished with value: -4.8799122674617035 and parameters: {'embedding_dim': 114, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 15 with value: -1.0200922953932452.
+[I 2025-12-18 00:39:15,076] Trial 25 finished with value: -4.7864957799096075 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 15 with value: -1.0200922953932452.
+[I 2025-12-18 00:39:21,785] Trial 26 finished with value: -384.51006833686307 and parameters: {'embedding_dim': 94, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 15 with value: -1.0200922953932452.
+[I 2025-12-18 00:39:35,260] Trial 27 finished with value: -44.98940459417737 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 15 with value: -1.0200922953932452.
+[I 2025-12-18 00:39:41,040] Trial 28 finished with value: -98.09516233870836 and parameters: {'embedding_dim': 115, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -1.0200922953932452.
+[I 2025-12-18 00:40:12,209] Trial 29 finished with value: -44.0712684419302 and parameters: {'embedding_dim': 124, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 15 with value: -1.0200922953932452.
+[I 2025-12-18 00:40:35,140] Trial 30 finished with value: -3.4498591503572387 and parameters: {'embedding_dim': 88, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 15 with value: -1.0200922953932452.
+[I 2025-12-18 00:40:58,138] Trial 31 finished with value: -35.156677657788684 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 15 with value: -1.0200922953932452.
+[I 2025-12-18 00:41:21,106] Trial 32 finished with value: -26.0700468374819 and parameters: {'embedding_dim': 99, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 15 with value: -1.0200922953932452.
+[I 2025-12-18 00:41:44,343] Trial 33 finished with value: -0.90335859497911 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 33 with value: -0.90335859497911.
+[I 2025-12-18 00:42:07,276] Trial 34 finished with value: -10.979019504387432 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 33 with value: -0.90335859497911.
+[I 2025-12-18 00:42:30,265] Trial 35 finished with value: -62.41620227408331 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 33 with value: -0.90335859497911.
+[I 2025-12-18 00:42:53,285] Trial 36 finished with value: -29.005304669036256 and parameters: {'embedding_dim': 71, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 33 with value: -0.90335859497911.
+[I 2025-12-18 00:42:59,924] Trial 37 finished with value: -37.86363352682385 and parameters: {'embedding_dim': 84, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 33 with value: -0.90335859497911.
+[I 2025-12-18 00:43:05,657] Trial 38 finished with value: -12.457400556425819 and parameters: {'embedding_dim': 110, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 33 with value: -0.90335859497911.
+[I 2025-12-18 00:43:36,605] Trial 39 finished with value: -4.087292854861162 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 33 with value: -0.90335859497911.
+[I 2025-12-18 00:43:46,654] Trial 40 finished with value: -16.11033777155839 and parameters: {'embedding_dim': 85, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 33 with value: -0.90335859497911.
+[I 2025-12-18 00:44:09,516] Trial 41 finished with value: -15.127443827264877 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 33 with value: -0.90335859497911.
+[I 2025-12-18 00:44:32,572] Trial 42 finished with value: -3.525529890262418 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 33 with value: -0.90335859497911.
+[I 2025-12-18 00:44:55,491] Trial 43 finished with value: -4.832380984892366 and parameters: {'embedding_dim': 88, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 33 with value: -0.90335859497911.
+[I 2025-12-18 00:45:18,725] Trial 44 finished with value: -95.30547820746297 and parameters: {'embedding_dim': 80, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 33 with value: -0.90335859497911.
+[I 2025-12-18 00:45:41,602] Trial 45 finished with value: -40.068311151262805 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 33 with value: -0.90335859497911.
+[I 2025-12-18 00:45:56,462] Trial 46 finished with value: -15.77087772627107 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 33 with value: -0.90335859497911.
+[I 2025-12-18 00:46:02,331] Trial 47 finished with value: -3.2360107585934283 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 33 with value: -0.90335859497911.
+[I 2025-12-18 00:46:12,560] Trial 48 finished with value: -18.479736554540047 and parameters: {'embedding_dim': 110, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 33 with value: -0.90335859497911.
+[I 2025-12-18 00:46:37,585] Trial 49 finished with value: -19.967572452729243 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 33 with value: -0.90335859497911.
+[I 2025-12-18 00:47:02,911] A new study created in memory with name: no-name-78573764-674f-4d92-92dc-1613c89b36f5
+Using device: cuda
+Processing ../../data/data_for_modeling/incheon_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/incheon_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-18 00:47:58,848] Trial 0 finished with value: -1223.608198715569 and parameters: {'embedding_dim': 353, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 0 with value: -1223.608198715569.
+[I 2025-12-18 00:48:42,889] Trial 1 finished with value: -754.4231725263207 and parameters: {'embedding_dim': 265, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 1 with value: -754.4231725263207.
+[I 2025-12-18 00:49:44,735] Trial 2 finished with value: -1850.67544099325 and parameters: {'embedding_dim': 460, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 1 with value: -754.4231725263207.
+[I 2025-12-18 00:50:00,192] Trial 3 finished with value: -150.04947192833012 and parameters: {'embedding_dim': 369, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 3 with value: -150.04947192833012.
+[I 2025-12-18 00:50:26,306] Trial 4 finished with value: -438.92372696961155 and parameters: {'embedding_dim': 469, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 3 with value: -150.04947192833012.
+[I 2025-12-18 00:51:03,789] Trial 5 finished with value: -1910.7038243281902 and parameters: {'embedding_dim': 458, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 3 with value: -150.04947192833012.
+[I 2025-12-18 00:51:42,354] Trial 6 finished with value: -86.26678756853903 and parameters: {'embedding_dim': 384, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 6 with value: -86.26678756853903.
+[I 2025-12-18 00:53:00,126] Trial 7 finished with value: -930.603027251188 and parameters: {'embedding_dim': 365, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 6 with value: -86.26678756853903.
+[I 2025-12-18 00:54:19,168] Trial 8 finished with value: -640.1003237042445 and parameters: {'embedding_dim': 136, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 6 with value: -86.26678756853903.
+[I 2025-12-18 00:55:31,072] Trial 9 finished with value: -320.29738505970784 and parameters: {'embedding_dim': 349, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 6 with value: -86.26678756853903.
+[I 2025-12-18 00:57:34,130] Trial 10 finished with value: -446.70903194456304 and parameters: {'embedding_dim': 250, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 6 with value: -86.26678756853903.
+[I 2025-12-18 00:57:48,763] Trial 11 finished with value: -340.1797513783028 and parameters: {'embedding_dim': 400, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 6 with value: -86.26678756853903.
+[I 2025-12-18 00:58:03,456] Trial 12 finished with value: -168.58941718601974 and parameters: {'embedding_dim': 280, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 6 with value: -86.26678756853903.
+[I 2025-12-18 00:58:17,147] Trial 13 finished with value: -556.5038847847117 and parameters: {'embedding_dim': 406, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 6 with value: -86.26678756853903.
+[I 2025-12-18 00:58:38,298] Trial 14 finished with value: -593.7001089639056 and parameters: {'embedding_dim': 303, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 6 with value: -86.26678756853903.
+[I 2025-12-18 00:59:13,815] Trial 15 finished with value: -296.762241640474 and parameters: {'embedding_dim': 211, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 6 with value: -86.26678756853903.
+[I 2025-12-18 00:59:45,487] Trial 16 finished with value: -714.7424667946418 and parameters: {'embedding_dim': 415, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 6 with value: -86.26678756853903.
+[I 2025-12-18 01:00:00,703] Trial 17 finished with value: -5692.911619674815 and parameters: {'embedding_dim': 495, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 6 with value: -86.26678756853903.
+[I 2025-12-18 01:00:35,080] Trial 18 finished with value: -243.6395916002943 and parameters: {'embedding_dim': 327, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 6 with value: -86.26678756853903.
+[I 2025-12-18 01:01:12,356] Trial 19 finished with value: -272.0478519105804 and parameters: {'embedding_dim': 388, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 6 with value: -86.26678756853903.
+[I 2025-12-18 01:01:43,575] Trial 20 finished with value: -97.52661816807989 and parameters: {'embedding_dim': 226, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 6 with value: -86.26678756853903.
+[I 2025-12-18 01:02:16,028] Trial 21 finished with value: -114.88155609280065 and parameters: {'embedding_dim': 192, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 6 with value: -86.26678756853903.
+[I 2025-12-18 01:02:46,678] Trial 22 finished with value: -439.2936167515464 and parameters: {'embedding_dim': 184, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 6 with value: -86.26678756853903.
+[I 2025-12-18 01:03:17,892] Trial 23 finished with value: -358.63484448653344 and parameters: {'embedding_dim': 212, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 6 with value: -86.26678756853903.
+[I 2025-12-18 01:03:48,684] Trial 24 finished with value: -934.1677977826392 and parameters: {'embedding_dim': 144, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 6 with value: -86.26678756853903.
+[I 2025-12-18 01:04:55,750] Trial 25 finished with value: -301.8754836064153 and parameters: {'embedding_dim': 167, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 6 with value: -86.26678756853903.
+[I 2025-12-18 01:05:26,867] Trial 26 finished with value: -275.23861863598563 and parameters: {'embedding_dim': 232, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 6 with value: -86.26678756853903.
+[I 2025-12-18 01:05:58,297] Trial 27 finished with value: -895.8364099719965 and parameters: {'embedding_dim': 304, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 6 with value: -86.26678756853903.
+[I 2025-12-18 01:07:52,460] Trial 28 finished with value: -21.659390118734404 and parameters: {'embedding_dim': 185, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 28 with value: -21.659390118734404.
+[I 2025-12-18 01:09:46,355] Trial 29 finished with value: -148.36458138161206 and parameters: {'embedding_dim': 237, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 28 with value: -21.659390118734404.
+[I 2025-12-18 01:11:40,608] A new study created in memory with name: no-name-ea155fdb-76b6-4fe7-b2be-4516d0ef34a8
+[I 2025-12-18 01:11:47,777] Trial 0 finished with value: -41.44825364562757 and parameters: {'embedding_dim': 109, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -41.44825364562757.
+[I 2025-12-18 01:11:52,800] Trial 1 finished with value: -19.094430591286 and parameters: {'embedding_dim': 70, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -19.094430591286.
+[I 2025-12-18 01:11:57,621] Trial 2 finished with value: -83.86170961780124 and parameters: {'embedding_dim': 110, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -19.094430591286.
+[I 2025-12-18 01:12:02,920] Trial 3 finished with value: -20.911283759597616 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -19.094430591286.
+[I 2025-12-18 01:12:07,977] Trial 4 finished with value: -495.81217383450354 and parameters: {'embedding_dim': 123, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -19.094430591286.
+[I 2025-12-18 01:12:15,172] Trial 5 finished with value: -177.62914893608544 and parameters: {'embedding_dim': 96, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -19.094430591286.
+[I 2025-12-18 01:12:20,196] Trial 6 finished with value: -89.46251982122742 and parameters: {'embedding_dim': 123, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -19.094430591286.
+[I 2025-12-18 01:12:27,379] Trial 7 finished with value: -21.879721353381562 and parameters: {'embedding_dim': 68, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -19.094430591286.
+[I 2025-12-18 01:12:34,137] Trial 8 finished with value: -37.26352448880323 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 1 with value: -19.094430591286.
+[I 2025-12-18 01:12:37,332] Trial 9 finished with value: -0.12392635602418588 and parameters: {'embedding_dim': 109, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:12:40,457] Trial 10 finished with value: -104.60324631335507 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:12:43,602] Trial 11 finished with value: -14.160461658044685 and parameters: {'embedding_dim': 66, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:12:46,766] Trial 12 finished with value: -43.26071891321595 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:12:49,858] Trial 13 finished with value: -174.76858029836336 and parameters: {'embedding_dim': 105, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:12:52,983] Trial 14 finished with value: -97.18485612163494 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:12:56,120] Trial 15 finished with value: -140.7514798722637 and parameters: {'embedding_dim': 116, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:12:59,313] Trial 16 finished with value: -165.32409060818654 and parameters: {'embedding_dim': 99, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:13:02,506] Trial 17 finished with value: -49.81023800717393 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:13:05,669] Trial 18 finished with value: -45.4184613724868 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:13:08,820] Trial 19 finished with value: -9.246322923833473 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:13:13,595] Trial 20 finished with value: -230.76732083507352 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:13:16,778] Trial 21 finished with value: -190.4735419233017 and parameters: {'embedding_dim': 117, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:13:20,006] Trial 22 finished with value: -69.81773204495398 and parameters: {'embedding_dim': 117, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:13:23,177] Trial 23 finished with value: -198.5757688554846 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:13:26,327] Trial 24 finished with value: -14.447825876753779 and parameters: {'embedding_dim': 102, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:13:31,153] Trial 25 finished with value: -46.47684942279756 and parameters: {'embedding_dim': 91, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:13:34,349] Trial 26 finished with value: -6.079217000209342 and parameters: {'embedding_dim': 113, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:13:37,485] Trial 27 finished with value: -230.88666191658965 and parameters: {'embedding_dim': 113, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:13:42,526] Trial 28 finished with value: -61.41146378118251 and parameters: {'embedding_dim': 121, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:13:45,927] Trial 29 finished with value: -75.90426002913667 and parameters: {'embedding_dim': 110, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:13:49,423] Trial 30 finished with value: -121.42389012999791 and parameters: {'embedding_dim': 120, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:13:52,559] Trial 31 finished with value: -186.47926321558796 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:13:55,699] Trial 32 finished with value: -11.431815096621945 and parameters: {'embedding_dim': 113, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:13:58,875] Trial 33 finished with value: -61.76455151041607 and parameters: {'embedding_dim': 112, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:14:03,643] Trial 34 finished with value: -21.781368244368966 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:14:08,469] Trial 35 finished with value: -78.7312851431313 and parameters: {'embedding_dim': 114, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:14:11,720] Trial 36 finished with value: -21.617130662256223 and parameters: {'embedding_dim': 108, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:14:16,550] Trial 37 finished with value: -41.883728569672044 and parameters: {'embedding_dim': 125, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:14:19,958] Trial 38 finished with value: -118.22509923597312 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:14:24,968] Trial 39 finished with value: -4.232912106420719 and parameters: {'embedding_dim': 95, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:14:31,852] Trial 40 finished with value: -162.51880322529053 and parameters: {'embedding_dim': 96, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:14:36,814] Trial 41 finished with value: -5.520797093920365 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:14:41,776] Trial 42 finished with value: -27.56064682763519 and parameters: {'embedding_dim': 94, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:14:46,768] Trial 43 finished with value: -26.36197662585942 and parameters: {'embedding_dim': 85, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:14:53,934] Trial 44 finished with value: -41.55924364721399 and parameters: {'embedding_dim': 85, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:14:59,098] Trial 45 finished with value: -70.78938962773054 and parameters: {'embedding_dim': 102, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:15:04,119] Trial 46 finished with value: -8.756748013101966 and parameters: {'embedding_dim': 99, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:15:09,205] Trial 47 finished with value: -4.562230715649783 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:15:14,315] Trial 48 finished with value: -9.864265479231516 and parameters: {'embedding_dim': 88, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:15:19,393] Trial 49 finished with value: -172.11406471201812 and parameters: {'embedding_dim': 94, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 9 with value: -0.12392635602418588.
+[I 2025-12-18 01:15:23,249] A new study created in memory with name: no-name-5956d37c-4a48-4b17-9ca1-32ab68ddb728
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_20000_1_incheon_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_20000_1_incheon_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan20000_1_incheon.csv: Class 0=17968 | Class 1=19334
+Saved ../../data/data_oversampled/ctgan20000/ctgan20000_1_incheon.csv: Class 0=17968 | Class 1=19334 | Class 2=14554
+Processing ../../data/data_for_modeling/seoul_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/seoul_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-18 01:16:19,218] Trial 0 finished with value: -485.76516526959546 and parameters: {'embedding_dim': 314, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -485.76516526959546.
+[I 2025-12-18 01:17:00,995] Trial 1 finished with value: -709.386676407724 and parameters: {'embedding_dim': 440, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 0 with value: -485.76516526959546.
+[I 2025-12-18 01:17:35,544] Trial 2 finished with value: -1590.450053266527 and parameters: {'embedding_dim': 481, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 0 with value: -485.76516526959546.
+[I 2025-12-18 01:17:55,726] Trial 3 finished with value: -372.0597117181526 and parameters: {'embedding_dim': 297, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 3 with value: -372.0597117181526.
+[I 2025-12-18 01:18:09,713] Trial 4 finished with value: -1821.896500573846 and parameters: {'embedding_dim': 380, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 3 with value: -372.0597117181526.
+[I 2025-12-18 01:18:51,363] Trial 5 finished with value: -2596.714728192546 and parameters: {'embedding_dim': 457, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 3 with value: -372.0597117181526.
+[I 2025-12-18 01:19:18,986] Trial 6 finished with value: -575.5838171430483 and parameters: {'embedding_dim': 242, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 3 with value: -372.0597117181526.
+[I 2025-12-18 01:20:00,977] Trial 7 finished with value: -116.90630838258865 and parameters: {'embedding_dim': 290, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 7 with value: -116.90630838258865.
+[I 2025-12-18 01:20:21,182] Trial 8 finished with value: -792.0915987497298 and parameters: {'embedding_dim': 501, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 7 with value: -116.90630838258865.
+[I 2025-12-18 01:20:46,316] Trial 9 finished with value: -489.8344541955079 and parameters: {'embedding_dim': 281, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 7 with value: -116.90630838258865.
+[I 2025-12-18 01:21:14,661] Trial 10 finished with value: -311.91540381317714 and parameters: {'embedding_dim': 159, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -116.90630838258865.
+[I 2025-12-18 01:21:43,381] Trial 11 finished with value: -852.0917411673609 and parameters: {'embedding_dim': 138, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -116.90630838258865.
+[I 2025-12-18 01:22:24,758] Trial 12 finished with value: -523.7325537386223 and parameters: {'embedding_dim': 168, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 7 with value: -116.90630838258865.
+[I 2025-12-18 01:22:55,031] Trial 13 finished with value: -285.8909667960125 and parameters: {'embedding_dim': 200, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -116.90630838258865.
+[I 2025-12-18 01:23:36,752] Trial 14 finished with value: -863.5608995721132 and parameters: {'embedding_dim': 228, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 7 with value: -116.90630838258865.
+[I 2025-12-18 01:24:04,464] Trial 15 finished with value: -931.6908498975054 and parameters: {'embedding_dim': 381, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -116.90630838258865.
+[I 2025-12-18 01:24:46,342] Trial 16 finished with value: -2325.0746725623976 and parameters: {'embedding_dim': 212, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 7 with value: -116.90630838258865.
+[I 2025-12-18 01:25:14,411] Trial 17 finished with value: -472.3982001561292 and parameters: {'embedding_dim': 258, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -116.90630838258865.
+[I 2025-12-18 01:25:46,048] Trial 18 finished with value: -1519.621868310024 and parameters: {'embedding_dim': 360, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 7 with value: -116.90630838258865.
+[I 2025-12-18 01:25:57,892] Trial 19 finished with value: -1313.838802019148 and parameters: {'embedding_dim': 190, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 7 with value: -116.90630838258865.
+[I 2025-12-18 01:27:11,488] Trial 20 finished with value: -316.95816550550666 and parameters: {'embedding_dim': 342, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 7 with value: -116.90630838258865.
+[I 2025-12-18 01:27:38,565] Trial 21 finished with value: -1875.9665087021242 and parameters: {'embedding_dim': 133, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -116.90630838258865.
+[I 2025-12-18 01:28:06,527] Trial 22 finished with value: -412.04927779432074 and parameters: {'embedding_dim': 174, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -116.90630838258865.
+[I 2025-12-18 01:28:33,269] Trial 23 finished with value: -403.03204400985453 and parameters: {'embedding_dim': 202, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -116.90630838258865.
+[I 2025-12-18 01:29:15,140] Trial 24 finished with value: -1120.6223395561087 and parameters: {'embedding_dim': 270, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 7 with value: -116.90630838258865.
+[I 2025-12-18 01:29:44,670] Trial 25 finished with value: -1148.3730540094155 and parameters: {'embedding_dim': 159, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -116.90630838258865.
+[I 2025-12-18 01:30:28,016] Trial 26 finished with value: -406.14694624088514 and parameters: {'embedding_dim': 225, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 7 with value: -116.90630838258865.
+[I 2025-12-18 01:30:56,163] Trial 27 finished with value: -2688.2834682247885 and parameters: {'embedding_dim': 189, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -116.90630838258865.
+[I 2025-12-18 01:31:07,631] Trial 28 finished with value: -596.2925310746631 and parameters: {'embedding_dim': 244, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 7 with value: -116.90630838258865.
+[I 2025-12-18 01:31:40,391] Trial 29 finished with value: -304.6901640699231 and parameters: {'embedding_dim': 299, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 7 with value: -116.90630838258865.
+[I 2025-12-18 01:32:22,900] A new study created in memory with name: no-name-683255d4-9ccb-4b69-9245-fd3e5d2b86f0
+[I 2025-12-18 01:32:30,229] Trial 0 finished with value: -30.8357229353442 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -30.8357229353442.
+[I 2025-12-18 01:32:35,444] Trial 1 finished with value: -23.338746610062685 and parameters: {'embedding_dim': 99, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -23.338746610062685.
+[I 2025-12-18 01:32:44,934] Trial 2 finished with value: -39.308004435657885 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 1 with value: -23.338746610062685.
+[I 2025-12-18 01:32:51,984] Trial 3 finished with value: -8.55624676580022 and parameters: {'embedding_dim': 65, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 3 with value: -8.55624676580022.
+[I 2025-12-18 01:32:59,209] Trial 4 finished with value: -8.404637473023808 and parameters: {'embedding_dim': 66, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -8.404637473023808.
+[I 2025-12-18 01:33:04,060] Trial 5 finished with value: -100.19837425150844 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 4 with value: -8.404637473023808.
+[I 2025-12-18 01:33:07,275] Trial 6 finished with value: -50.63724534618492 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 4 with value: -8.404637473023808.
+[I 2025-12-18 01:33:10,746] Trial 7 finished with value: -56.849139566942824 and parameters: {'embedding_dim': 122, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 4 with value: -8.404637473023808.
+[I 2025-12-18 01:33:17,329] Trial 8 finished with value: -12.47688333054607 and parameters: {'embedding_dim': 98, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 4 with value: -8.404637473023808.
+[I 2025-12-18 01:33:24,065] Trial 9 finished with value: -39.065666770009855 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 4 with value: -8.404637473023808.
+[I 2025-12-18 01:33:31,240] Trial 10 finished with value: -19.980361306008014 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -8.404637473023808.
+[I 2025-12-18 01:33:36,283] Trial 11 finished with value: -97.29896797841118 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -8.404637473023808.
+[I 2025-12-18 01:33:41,642] Trial 12 finished with value: -31.059001303859013 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -8.404637473023808.
+[I 2025-12-18 01:33:44,971] Trial 13 finished with value: -312.57217528155905 and parameters: {'embedding_dim': 76, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 4 with value: -8.404637473023808.
+[I 2025-12-18 01:33:50,370] Trial 14 finished with value: -96.30778934681487 and parameters: {'embedding_dim': 71, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -8.404637473023808.
+[I 2025-12-18 01:33:55,399] Trial 15 finished with value: -14.488047129355554 and parameters: {'embedding_dim': 85, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -8.404637473023808.
+[I 2025-12-18 01:34:02,588] Trial 16 finished with value: -8.839814511924452 and parameters: {'embedding_dim': 115, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -8.404637473023808.
+[I 2025-12-18 01:34:05,909] Trial 17 finished with value: -63.36874828815103 and parameters: {'embedding_dim': 70, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 4 with value: -8.404637473023808.
+[I 2025-12-18 01:34:11,220] Trial 18 finished with value: -44.79614048363431 and parameters: {'embedding_dim': 85, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -8.404637473023808.
+[I 2025-12-18 01:34:17,965] Trial 19 finished with value: -184.41738703235686 and parameters: {'embedding_dim': 110, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 4 with value: -8.404637473023808.
+[I 2025-12-18 01:34:23,296] Trial 20 finished with value: -52.246317094767484 and parameters: {'embedding_dim': 70, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -8.404637473023808.
+[I 2025-12-18 01:34:30,505] Trial 21 finished with value: -6.72401871543139 and parameters: {'embedding_dim': 126, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:34:37,793] Trial 22 finished with value: -41.73663645357519 and parameters: {'embedding_dim': 128, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:34:44,975] Trial 23 finished with value: -41.99143010217669 and parameters: {'embedding_dim': 109, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:34:50,333] Trial 24 finished with value: -87.55051139370454 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:34:57,059] Trial 25 finished with value: -71.62635284872746 and parameters: {'embedding_dim': 122, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:35:04,210] Trial 26 finished with value: -39.23409721058641 and parameters: {'embedding_dim': 67, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:35:09,564] Trial 27 finished with value: -60.80454321093471 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:35:16,091] Trial 28 finished with value: -303.19667169112677 and parameters: {'embedding_dim': 105, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:35:22,830] Trial 29 finished with value: -36.468681317469674 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:35:28,265] Trial 30 finished with value: -49.893487578113046 and parameters: {'embedding_dim': 116, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:35:35,469] Trial 31 finished with value: -18.91929025770583 and parameters: {'embedding_dim': 128, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:35:42,722] Trial 32 finished with value: -27.577821587396315 and parameters: {'embedding_dim': 120, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:35:49,933] Trial 33 finished with value: -31.42174920893205 and parameters: {'embedding_dim': 116, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:35:57,147] Trial 34 finished with value: -17.00473703842808 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:36:02,029] Trial 35 finished with value: -56.71488383788095 and parameters: {'embedding_dim': 114, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:36:09,226] Trial 36 finished with value: -35.62023715689182 and parameters: {'embedding_dim': 123, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:36:15,721] Trial 37 finished with value: -83.91266026054372 and parameters: {'embedding_dim': 126, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:36:19,138] Trial 38 finished with value: -19.464001604942062 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:36:24,510] Trial 39 finished with value: -79.26428214214036 and parameters: {'embedding_dim': 111, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:36:30,974] Trial 40 finished with value: -34.11088086616175 and parameters: {'embedding_dim': 67, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:36:37,539] Trial 41 finished with value: -16.554609010725972 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:36:44,111] Trial 42 finished with value: -190.31963427187836 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:36:51,031] Trial 43 finished with value: -26.497216644245455 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:36:57,617] Trial 44 finished with value: -43.84196058482836 and parameters: {'embedding_dim': 106, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:37:02,665] Trial 45 finished with value: -50.38960223750277 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 21 with value: -6.72401871543139.
+[I 2025-12-18 01:37:09,868] Trial 46 finished with value: -5.922993181926361 and parameters: {'embedding_dim': 73, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 46 with value: -5.922993181926361.
+[I 2025-12-18 01:37:17,106] Trial 47 finished with value: -92.86227299285875 and parameters: {'embedding_dim': 74, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 46 with value: -5.922993181926361.
+[I 2025-12-18 01:37:22,449] Trial 48 finished with value: -137.43529434201534 and parameters: {'embedding_dim': 81, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 46 with value: -5.922993181926361.
+[I 2025-12-18 01:37:29,647] Trial 49 finished with value: -72.39712548410989 and parameters: {'embedding_dim': 67, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 46 with value: -5.922993181926361.
+[I 2025-12-18 01:37:37,082] A new study created in memory with name: no-name-381dfa5b-98ab-4fb9-bdd4-5d1a42225167
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_20000_1_seoul_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_20000_1_seoul_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan20000_1_seoul.csv: Class 0=19250 | Class 1=18642
+Saved ../../data/data_oversampled/ctgan20000/ctgan20000_1_seoul.csv: Class 0=19250 | Class 1=18642 | Class 2=15676
+Processing ../../data/data_for_modeling/busan_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/busan_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-18 01:38:03,447] Trial 0 finished with value: -1517.04831984882 and parameters: {'embedding_dim': 194, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -1517.04831984882.
+[I 2025-12-18 01:38:17,047] Trial 1 finished with value: -121.06016841140479 and parameters: {'embedding_dim': 425, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:38:51,965] Trial 2 finished with value: -1794.9908608916667 and parameters: {'embedding_dim': 408, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:38:58,792] Trial 3 finished with value: -595.2289011855576 and parameters: {'embedding_dim': 195, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:39:22,281] Trial 4 finished with value: -2655.047720640166 and parameters: {'embedding_dim': 331, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:39:39,146] Trial 5 finished with value: -725.1909504122159 and parameters: {'embedding_dim': 450, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:39:54,011] Trial 6 finished with value: -448.22712169983805 and parameters: {'embedding_dim': 305, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:40:03,595] Trial 7 finished with value: -2306.4757730799656 and parameters: {'embedding_dim': 351, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:40:21,484] Trial 8 finished with value: -815.0426789333743 and parameters: {'embedding_dim': 244, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:40:33,514] Trial 9 finished with value: -668.4054104100549 and parameters: {'embedding_dim': 369, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:40:43,266] Trial 10 finished with value: -541.1205596756588 and parameters: {'embedding_dim': 504, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:40:56,687] Trial 11 finished with value: -392.43555435022574 and parameters: {'embedding_dim': 278, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:41:09,839] Trial 12 finished with value: -694.3918102238364 and parameters: {'embedding_dim': 270, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:41:23,694] Trial 13 finished with value: -1110.695930697097 and parameters: {'embedding_dim': 432, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:41:39,902] Trial 14 finished with value: -400.3008589052582 and parameters: {'embedding_dim': 128, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:42:03,899] Trial 15 finished with value: -248.81945499112805 and parameters: {'embedding_dim': 488, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:42:16,205] Trial 16 finished with value: -2604.743468279147 and parameters: {'embedding_dim': 478, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:42:34,478] Trial 17 finished with value: -1232.9321140423042 and parameters: {'embedding_dim': 395, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:42:58,278] Trial 18 finished with value: -331.8791962773195 and parameters: {'embedding_dim': 508, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:43:10,298] Trial 19 finished with value: -6699.788278451096 and parameters: {'embedding_dim': 451, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:43:28,181] Trial 20 finished with value: -916.7028141161608 and parameters: {'embedding_dim': 388, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:43:51,989] Trial 21 finished with value: -1140.374423015991 and parameters: {'embedding_dim': 510, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:44:15,759] Trial 22 finished with value: -1977.215575454219 and parameters: {'embedding_dim': 478, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:44:39,605] Trial 23 finished with value: -823.0960804529618 and parameters: {'embedding_dim': 470, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:45:03,134] Trial 24 finished with value: -641.9004876276275 and parameters: {'embedding_dim': 426, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:45:18,668] Trial 25 finished with value: -3319.6419292529126 and parameters: {'embedding_dim': 511, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:45:37,049] Trial 26 finished with value: -632.0616157730316 and parameters: {'embedding_dim': 466, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:46:00,240] Trial 27 finished with value: -945.0942600958782 and parameters: {'embedding_dim': 427, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:46:13,303] Trial 28 finished with value: -926.7008598593684 and parameters: {'embedding_dim': 489, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:46:37,555] Trial 29 finished with value: -2523.131442973172 and parameters: {'embedding_dim': 446, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -121.06016841140479.
+[I 2025-12-18 01:46:50,567] A new study created in memory with name: no-name-6543ce7d-2acb-4fd1-b25d-bc04f7d20277
+[I 2025-12-18 01:46:56,928] Trial 0 finished with value: -96.10592619889773 and parameters: {'embedding_dim': 67, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -96.10592619889773.
+[I 2025-12-18 01:47:01,822] Trial 1 finished with value: -333.7442171741113 and parameters: {'embedding_dim': 66, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -96.10592619889773.
+[I 2025-12-18 01:47:08,182] Trial 2 finished with value: -26.420504415921556 and parameters: {'embedding_dim': 89, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -26.420504415921556.
+[I 2025-12-18 01:47:11,584] Trial 3 finished with value: -64.26821460865497 and parameters: {'embedding_dim': 76, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -26.420504415921556.
+[I 2025-12-18 01:47:14,945] Trial 4 finished with value: -168.63979569444376 and parameters: {'embedding_dim': 94, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -26.420504415921556.
+[I 2025-12-18 01:47:18,086] Trial 5 finished with value: -106.32055099126187 and parameters: {'embedding_dim': 125, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 2 with value: -26.420504415921556.
+[I 2025-12-18 01:47:21,328] Trial 6 finished with value: -191.3581084409031 and parameters: {'embedding_dim': 87, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -26.420504415921556.
+[I 2025-12-18 01:47:24,534] Trial 7 finished with value: -247.5434484239539 and parameters: {'embedding_dim': 125, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -26.420504415921556.
+[I 2025-12-18 01:47:31,644] Trial 8 finished with value: -78.96668756623808 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -26.420504415921556.
+[I 2025-12-18 01:47:36,562] Trial 9 finished with value: -93.87837155265171 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -26.420504415921556.
+[I 2025-12-18 01:47:42,935] Trial 10 finished with value: -104.79951050922953 and parameters: {'embedding_dim': 108, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -26.420504415921556.
+[I 2025-12-18 01:47:48,149] Trial 11 finished with value: -305.27545033342346 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -26.420504415921556.
+[I 2025-12-18 01:47:55,230] Trial 12 finished with value: -205.62322678916462 and parameters: {'embedding_dim': 79, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -26.420504415921556.
+[I 2025-12-18 01:48:00,025] Trial 13 finished with value: -234.19673146712665 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -26.420504415921556.
+[I 2025-12-18 01:48:05,265] Trial 14 finished with value: -14.598474053076071 and parameters: {'embedding_dim': 107, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:48:10,014] Trial 15 finished with value: -100.5384034117003 and parameters: {'embedding_dim': 112, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:48:17,124] Trial 16 finished with value: -311.64465989499934 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:48:21,879] Trial 17 finished with value: -96.76132918016512 and parameters: {'embedding_dim': 115, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:48:27,100] Trial 18 finished with value: -60.815566181061016 and parameters: {'embedding_dim': 117, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:48:33,445] Trial 19 finished with value: -48.22906984287135 and parameters: {'embedding_dim': 98, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:48:40,502] Trial 20 finished with value: -33.65703655771221 and parameters: {'embedding_dim': 89, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:48:47,577] Trial 21 finished with value: -65.13963144381663 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:48:54,681] Trial 22 finished with value: -130.27487769532257 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:48:59,899] Trial 23 finished with value: -39.21003455580565 and parameters: {'embedding_dim': 104, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:49:06,873] Trial 24 finished with value: -63.48931868924925 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:49:13,123] Trial 25 finished with value: -137.60986495950948 and parameters: {'embedding_dim': 100, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:49:18,427] Trial 26 finished with value: -203.6241975815987 and parameters: {'embedding_dim': 83, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:49:25,510] Trial 27 finished with value: -63.41957105989806 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:49:30,458] Trial 28 finished with value: -24.498784785019936 and parameters: {'embedding_dim': 91, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:49:35,411] Trial 29 finished with value: -98.07160997079669 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:49:40,355] Trial 30 finished with value: -126.05071462880953 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:49:45,221] Trial 31 finished with value: -314.1592837064219 and parameters: {'embedding_dim': 90, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:49:51,891] Trial 32 finished with value: -84.74573861367554 and parameters: {'embedding_dim': 91, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:49:56,628] Trial 33 finished with value: -114.97790233563343 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:50:01,760] Trial 34 finished with value: -189.48655251033114 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:50:08,178] Trial 35 finished with value: -94.28093129473659 and parameters: {'embedding_dim': 88, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:50:11,566] Trial 36 finished with value: -474.43038074505444 and parameters: {'embedding_dim': 71, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:50:16,509] Trial 37 finished with value: -98.3946630722681 and parameters: {'embedding_dim': 121, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:50:19,889] Trial 38 finished with value: -282.49749762187025 and parameters: {'embedding_dim': 110, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:50:26,542] Trial 39 finished with value: -169.67032546592344 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:50:29,729] Trial 40 finished with value: -325.90814786870715 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:50:34,953] Trial 41 finished with value: -160.52090274288156 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:50:40,205] Trial 42 finished with value: -49.562506144643734 and parameters: {'embedding_dim': 107, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:50:45,424] Trial 43 finished with value: -40.01108473873937 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:50:50,729] Trial 44 finished with value: -145.79059313907376 and parameters: {'embedding_dim': 97, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:50:56,265] Trial 45 finished with value: -114.09041686492606 and parameters: {'embedding_dim': 108, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:51:01,468] Trial 46 finished with value: -213.92149080432208 and parameters: {'embedding_dim': 88, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:51:08,117] Trial 47 finished with value: -152.04532122156684 and parameters: {'embedding_dim': 81, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:51:12,855] Trial 48 finished with value: -113.61160015019217 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:51:18,079] Trial 49 finished with value: -159.20876586638235 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -14.598474053076071.
+[I 2025-12-18 01:51:23,578] A new study created in memory with name: no-name-70f66776-7895-4355-bdc4-16b6b02e29e3
+[I 2025-12-18 01:51:28,266] Trial 0 finished with value: -1368.2113066511097 and parameters: {'embedding_dim': 366, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 0 with value: -1368.2113066511097.
+[I 2025-12-18 01:51:40,064] Trial 1 finished with value: -406.0599196711299 and parameters: {'embedding_dim': 457, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 1 with value: -406.0599196711299.
+[I 2025-12-18 01:52:13,785] Trial 2 finished with value: -104.95603996377517 and parameters: {'embedding_dim': 254, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 2 with value: -104.95603996377517.
+[I 2025-12-18 01:52:27,416] Trial 3 finished with value: -356.74101586117587 and parameters: {'embedding_dim': 367, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 2 with value: -104.95603996377517.
+[I 2025-12-18 01:52:35,543] Trial 4 finished with value: -544.9291898408301 and parameters: {'embedding_dim': 416, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 2 with value: -104.95603996377517.
+[I 2025-12-18 01:53:04,791] Trial 5 finished with value: -2258.0953190623577 and parameters: {'embedding_dim': 234, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 2 with value: -104.95603996377517.
+[I 2025-12-18 01:53:23,448] Trial 6 finished with value: -730.4313026937473 and parameters: {'embedding_dim': 217, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -104.95603996377517.
+[I 2025-12-18 01:53:36,649] Trial 7 finished with value: -407.0675925319374 and parameters: {'embedding_dim': 129, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 2 with value: -104.95603996377517.
+[I 2025-12-18 01:54:06,066] Trial 8 finished with value: -832.7464616060415 and parameters: {'embedding_dim': 282, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 2 with value: -104.95603996377517.
+[I 2025-12-18 01:54:24,262] Trial 9 finished with value: -325.76482423217504 and parameters: {'embedding_dim': 474, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 2 with value: -104.95603996377517.
+[I 2025-12-18 01:54:57,421] Trial 10 finished with value: -1506.7431466650833 and parameters: {'embedding_dim': 163, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 2 with value: -104.95603996377517.
+[I 2025-12-18 01:55:16,898] Trial 11 finished with value: -713.1019272920761 and parameters: {'embedding_dim': 498, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 2 with value: -104.95603996377517.
+[I 2025-12-18 01:55:34,767] Trial 12 finished with value: -414.8226321960301 and parameters: {'embedding_dim': 310, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 2 with value: -104.95603996377517.
+[I 2025-12-18 01:55:56,964] Trial 13 finished with value: -117.09846870397233 and parameters: {'embedding_dim': 257, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -104.95603996377517.
+[I 2025-12-18 01:56:20,873] Trial 14 finished with value: -445.1238342022896 and parameters: {'embedding_dim': 238, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -104.95603996377517.
+[I 2025-12-18 01:56:39,218] Trial 15 finished with value: -520.6326114788251 and parameters: {'embedding_dim': 279, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -104.95603996377517.
+[I 2025-12-18 01:57:01,221] Trial 16 finished with value: -1249.0454506990286 and parameters: {'embedding_dim': 196, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -104.95603996377517.
+[I 2025-12-18 01:57:11,852] Trial 17 finished with value: -1290.8915843590196 and parameters: {'embedding_dim': 324, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -104.95603996377517.
+[I 2025-12-18 01:57:35,406] Trial 18 finished with value: -693.6077615333189 and parameters: {'embedding_dim': 265, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -104.95603996377517.
+[I 2025-12-18 01:57:51,601] Trial 19 finished with value: -152.34857480653517 and parameters: {'embedding_dim': 189, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -104.95603996377517.
+[I 2025-12-18 01:58:05,103] Trial 20 finished with value: -434.8278703688668 and parameters: {'embedding_dim': 340, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 2 with value: -104.95603996377517.
+[I 2025-12-18 01:58:22,771] Trial 21 finished with value: -1297.9427163676112 and parameters: {'embedding_dim': 179, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -104.95603996377517.
+[I 2025-12-18 01:58:46,103] Trial 22 finished with value: -726.0693832641973 and parameters: {'embedding_dim': 147, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -104.95603996377517.
+[I 2025-12-18 01:59:02,303] Trial 23 finished with value: -58.85720617580585 and parameters: {'embedding_dim': 199, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 23 with value: -58.85720617580585.
+[I 2025-12-18 01:59:12,850] Trial 24 finished with value: -924.0700120373403 and parameters: {'embedding_dim': 249, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 23 with value: -58.85720617580585.
+[I 2025-12-18 01:59:36,604] Trial 25 finished with value: -1243.533770136966 and parameters: {'embedding_dim': 213, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 23 with value: -58.85720617580585.
+[I 2025-12-18 01:59:52,840] Trial 26 finished with value: -1031.5337265308235 and parameters: {'embedding_dim': 298, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 23 with value: -58.85720617580585.
+[I 2025-12-18 02:00:22,034] Trial 27 finished with value: -746.5445891762606 and parameters: {'embedding_dim': 263, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 23 with value: -58.85720617580585.
+[I 2025-12-18 02:00:29,027] Trial 28 finished with value: -1275.4580909363758 and parameters: {'embedding_dim': 217, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 23 with value: -58.85720617580585.
+[I 2025-12-18 02:00:42,145] Trial 29 finished with value: -3430.4628600336837 and parameters: {'embedding_dim': 375, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 23 with value: -58.85720617580585.
+[I 2025-12-18 02:01:02,718] A new study created in memory with name: no-name-0f685ea0-e02a-4d1d-843f-af0946270c97
+[I 2025-12-18 02:01:09,645] Trial 0 finished with value: -342.4895151859073 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -342.4895151859073.
+[I 2025-12-18 02:01:18,962] Trial 1 finished with value: -48.89228553569707 and parameters: {'embedding_dim': 91, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -48.89228553569707.
+[I 2025-12-18 02:01:28,381] Trial 2 finished with value: -50.82806578648771 and parameters: {'embedding_dim': 68, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -48.89228553569707.
+[I 2025-12-18 02:01:34,841] Trial 3 finished with value: -50.65149168084794 and parameters: {'embedding_dim': 89, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -48.89228553569707.
+[I 2025-12-18 02:01:47,501] Trial 4 finished with value: -81.0503251669159 and parameters: {'embedding_dim': 67, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 1 with value: -48.89228553569707.
+[I 2025-12-18 02:01:53,120] Trial 5 finished with value: -48.5470310431851 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -48.5470310431851.
+[I 2025-12-18 02:01:59,278] Trial 6 finished with value: -71.6427850523908 and parameters: {'embedding_dim': 109, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 5 with value: -48.5470310431851.
+[I 2025-12-18 02:02:06,611] Trial 7 finished with value: -81.85760110323884 and parameters: {'embedding_dim': 99, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 5 with value: -48.5470310431851.
+[I 2025-12-18 02:02:10,213] Trial 8 finished with value: -66.5811777394672 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 5 with value: -48.5470310431851.
+[I 2025-12-18 02:02:19,688] Trial 9 finished with value: -96.09502894691718 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 5 with value: -48.5470310431851.
+[I 2025-12-18 02:02:23,402] Trial 10 finished with value: -98.302484269313 and parameters: {'embedding_dim': 83, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 5 with value: -48.5470310431851.
+[I 2025-12-18 02:02:29,247] Trial 11 finished with value: -107.82543386963268 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -48.5470310431851.
+[I 2025-12-18 02:02:34,734] Trial 12 finished with value: -27.21734047130171 and parameters: {'embedding_dim': 107, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 12 with value: -27.21734047130171.
+[I 2025-12-18 02:02:40,843] Trial 13 finished with value: -91.30535446947609 and parameters: {'embedding_dim': 111, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 12 with value: -27.21734047130171.
+[I 2025-12-18 02:02:49,798] Trial 14 finished with value: -38.89505150441655 and parameters: {'embedding_dim': 108, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 12 with value: -27.21734047130171.
+[I 2025-12-18 02:02:57,155] Trial 15 finished with value: -6.250424945119327 and parameters: {'embedding_dim': 115, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:03:04,528] Trial 16 finished with value: -44.36351230491395 and parameters: {'embedding_dim': 122, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:03:11,385] Trial 17 finished with value: -144.0909681156473 and parameters: {'embedding_dim': 115, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:03:15,170] Trial 18 finished with value: -283.6954613329575 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:03:20,716] Trial 19 finished with value: -18.118269704851667 and parameters: {'embedding_dim': 117, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:03:27,539] Trial 20 finished with value: -281.4774857817584 and parameters: {'embedding_dim': 118, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:03:33,023] Trial 21 finished with value: -66.30989169684483 and parameters: {'embedding_dim': 123, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:03:38,507] Trial 22 finished with value: -22.050768858976387 and parameters: {'embedding_dim': 102, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:03:43,985] Trial 23 finished with value: -38.25570982910732 and parameters: {'embedding_dim': 102, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:03:49,463] Trial 24 finished with value: -21.46681691526066 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:03:54,466] Trial 25 finished with value: -88.08369456312617 and parameters: {'embedding_dim': 115, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:03:59,928] Trial 26 finished with value: -36.3686993677276 and parameters: {'embedding_dim': 123, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:04:07,247] Trial 27 finished with value: -79.6082837467091 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:04:12,422] Trial 28 finished with value: -181.2762404348028 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:04:19,795] Trial 29 finished with value: -58.89015229380913 and parameters: {'embedding_dim': 126, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:04:26,710] Trial 30 finished with value: -136.16963410033424 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:04:32,194] Trial 31 finished with value: -90.51549196225535 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:04:37,675] Trial 32 finished with value: -28.190839281474382 and parameters: {'embedding_dim': 113, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:04:43,164] Trial 33 finished with value: -119.99590615237656 and parameters: {'embedding_dim': 118, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:04:52,614] Trial 34 finished with value: -73.09751950565624 and parameters: {'embedding_dim': 95, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:04:58,094] Trial 35 finished with value: -155.66560049878416 and parameters: {'embedding_dim': 106, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:05:05,439] Trial 36 finished with value: -72.40671180637432 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:05:11,461] Trial 37 finished with value: -415.6684800787875 and parameters: {'embedding_dim': 90, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:05:17,111] Trial 38 finished with value: -84.56011205420316 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:05:22,267] Trial 39 finished with value: -42.19008730698754 and parameters: {'embedding_dim': 94, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:05:31,539] Trial 40 finished with value: -7.005232977752862 and parameters: {'embedding_dim': 120, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:05:41,010] Trial 41 finished with value: -107.38131058077481 and parameters: {'embedding_dim': 120, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:05:50,862] Trial 42 finished with value: -77.23068696672598 and parameters: {'embedding_dim': 125, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:06:02,083] Trial 43 finished with value: -54.55551861421547 and parameters: {'embedding_dim': 112, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:06:11,342] Trial 44 finished with value: -56.394482224302905 and parameters: {'embedding_dim': 116, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:06:20,645] Trial 45 finished with value: -72.58875813984483 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:06:26,150] Trial 46 finished with value: -31.368203018818342 and parameters: {'embedding_dim': 109, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:06:31,611] Trial 47 finished with value: -224.03895598934872 and parameters: {'embedding_dim': 121, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:06:37,763] Trial 48 finished with value: -62.83536153280876 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:06:45,132] Trial 49 finished with value: -46.179764436151046 and parameters: {'embedding_dim': 86, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -6.250424945119327.
+[I 2025-12-18 02:06:55,051] A new study created in memory with name: no-name-c3dba5b6-8e25-4436-8c87-26021675ec17
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_20000_1_busan_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_20000_1_busan_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan20000_1_busan.csv: Class 0=16780 | Class 1=17522
+Saved ../../data/data_oversampled/ctgan20000/ctgan20000_1_busan.csv: Class 0=16780 | Class 1=17522 | Class 2=16492
+Processing ../../data/data_for_modeling/daegu_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/daegu_train.csv: Optimizing CTGAN for class 1...
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_20000_1_daegu_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_20000_1_daegu_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan20000_1_daegu.csv: Class 0=17329 | Class 1=17489
+Saved ../../data/data_oversampled/ctgan20000/ctgan20000_1_daegu.csv: Class 0=17329 | Class 1=17489 | Class 2=16582
+Processing ../../data/data_for_modeling/daejeon_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/daejeon_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-18 02:07:13,079] Trial 0 finished with value: -473.085569905589 and parameters: {'embedding_dim': 489, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 0 with value: -473.085569905589.
+[I 2025-12-18 02:07:28,533] Trial 1 finished with value: -801.535865943123 and parameters: {'embedding_dim': 476, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 0 with value: -473.085569905589.
+[I 2025-12-18 02:07:49,671] Trial 2 finished with value: -298.91249385845197 and parameters: {'embedding_dim': 178, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 2 with value: -298.91249385845197.
+[I 2025-12-18 02:09:10,808] Trial 3 finished with value: -591.9038146675209 and parameters: {'embedding_dim': 501, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 2 with value: -298.91249385845197.
+[I 2025-12-18 02:09:38,679] Trial 4 finished with value: -541.2306667876558 and parameters: {'embedding_dim': 322, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -298.91249385845197.
+[I 2025-12-18 02:09:49,760] Trial 5 finished with value: -842.0003508065379 and parameters: {'embedding_dim': 185, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 2 with value: -298.91249385845197.
+[I 2025-12-18 02:10:09,386] Trial 6 finished with value: -1303.4886411054963 and parameters: {'embedding_dim': 476, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 2 with value: -298.91249385845197.
+[I 2025-12-18 02:10:31,330] Trial 7 finished with value: -558.3974007720851 and parameters: {'embedding_dim': 386, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 2 with value: -298.91249385845197.
+[I 2025-12-18 02:11:05,262] Trial 8 finished with value: -724.7298777777257 and parameters: {'embedding_dim': 292, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 2 with value: -298.91249385845197.
+[I 2025-12-18 02:11:34,018] Trial 9 finished with value: -25.033815760682714 and parameters: {'embedding_dim': 371, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 9 with value: -25.033815760682714.
+[I 2025-12-18 02:12:05,209] Trial 10 finished with value: -933.7091134615557 and parameters: {'embedding_dim': 362, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 9 with value: -25.033815760682714.
+[I 2025-12-18 02:12:23,833] Trial 11 finished with value: -422.607305808211 and parameters: {'embedding_dim': 142, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 9 with value: -25.033815760682714.
+[I 2025-12-18 02:12:41,102] Trial 12 finished with value: -270.9263917255264 and parameters: {'embedding_dim': 241, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 9 with value: -25.033815760682714.
+[I 2025-12-18 02:13:18,661] Trial 13 finished with value: -674.4612309609231 and parameters: {'embedding_dim': 255, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 9 with value: -25.033815760682714.
+[I 2025-12-18 02:14:26,094] Trial 14 finished with value: -2378.913912187611 and parameters: {'embedding_dim': 243, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 9 with value: -25.033815760682714.
+[I 2025-12-18 02:14:37,789] Trial 15 finished with value: -3156.099539649246 and parameters: {'embedding_dim': 410, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 9 with value: -25.033815760682714.
+[I 2025-12-18 02:15:07,886] Trial 16 finished with value: -954.930798182337 and parameters: {'embedding_dim': 335, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 9 with value: -25.033815760682714.
+[I 2025-12-18 02:15:19,651] Trial 17 finished with value: -694.654187633059 and parameters: {'embedding_dim': 265, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 9 with value: -25.033815760682714.
+[I 2025-12-18 02:15:56,374] Trial 18 finished with value: -312.75757234177496 and parameters: {'embedding_dim': 424, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 9 with value: -25.033815760682714.
+[I 2025-12-18 02:17:03,652] Trial 19 finished with value: -28.648531333132546 and parameters: {'embedding_dim': 213, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 9 with value: -25.033815760682714.
+[I 2025-12-18 02:17:56,478] Trial 20 finished with value: -1035.3175585847366 and parameters: {'embedding_dim': 202, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 9 with value: -25.033815760682714.
+[I 2025-12-18 02:19:02,238] Trial 21 finished with value: -642.4308970175462 and parameters: {'embedding_dim': 222, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 9 with value: -25.033815760682714.
+[I 2025-12-18 02:20:07,801] Trial 22 finished with value: -313.3559786636371 and parameters: {'embedding_dim': 292, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 9 with value: -25.033815760682714.
+[I 2025-12-18 02:21:00,080] Trial 23 finished with value: -405.10038841880976 and parameters: {'embedding_dim': 152, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 9 with value: -25.033815760682714.
+[I 2025-12-18 02:22:06,997] Trial 24 finished with value: -249.9452412205351 and parameters: {'embedding_dim': 295, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 9 with value: -25.033815760682714.
+[I 2025-12-18 02:22:59,495] Trial 25 finished with value: -45.00911570535021 and parameters: {'embedding_dim': 362, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 9 with value: -25.033815760682714.
+[I 2025-12-18 02:23:39,207] Trial 26 finished with value: -812.1473676694404 and parameters: {'embedding_dim': 355, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 9 with value: -25.033815760682714.
+[I 2025-12-18 02:24:31,999] Trial 27 finished with value: -40.52013882902048 and parameters: {'embedding_dim': 440, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 9 with value: -25.033815760682714.
+[I 2025-12-18 02:25:25,028] Trial 28 finished with value: -622.953036878878 and parameters: {'embedding_dim': 434, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 9 with value: -25.033815760682714.
+[I 2025-12-18 02:25:46,563] Trial 29 finished with value: -800.7342692472115 and parameters: {'embedding_dim': 463, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 9 with value: -25.033815760682714.
+[I 2025-12-18 02:26:15,837] A new study created in memory with name: no-name-fa33e6b1-4eec-453d-97fd-e29833c16e8c
+[I 2025-12-18 02:26:19,138] Trial 0 finished with value: -662.3107641947074 and parameters: {'embedding_dim': 115, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -662.3107641947074.
+[I 2025-12-18 02:26:22,439] Trial 1 finished with value: -184.75082488553988 and parameters: {'embedding_dim': 68, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 1 with value: -184.75082488553988.
+[I 2025-12-18 02:26:29,219] Trial 2 finished with value: -90.92801085360766 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -90.92801085360766.
+[I 2025-12-18 02:26:34,651] Trial 3 finished with value: -246.19758048893559 and parameters: {'embedding_dim': 113, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -90.92801085360766.
+[I 2025-12-18 02:26:38,107] Trial 4 finished with value: -55.00989596857837 and parameters: {'embedding_dim': 73, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 4 with value: -55.00989596857837.
+[I 2025-12-18 02:26:41,334] Trial 5 finished with value: -55.89890526487351 and parameters: {'embedding_dim': 69, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 4 with value: -55.00989596857837.
+[I 2025-12-18 02:26:46,742] Trial 6 finished with value: -121.82238470524538 and parameters: {'embedding_dim': 122, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -55.00989596857837.
+[I 2025-12-18 02:26:51,744] Trial 7 finished with value: -87.60709263403353 and parameters: {'embedding_dim': 118, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -55.00989596857837.
+[I 2025-12-18 02:26:58,984] Trial 8 finished with value: -68.94471781334175 and parameters: {'embedding_dim': 110, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -55.00989596857837.
+[I 2025-12-18 02:27:04,313] Trial 9 finished with value: -62.09573691065397 and parameters: {'embedding_dim': 114, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -55.00989596857837.
+[I 2025-12-18 02:27:07,770] Trial 10 finished with value: -112.5413479490015 and parameters: {'embedding_dim': 88, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 4 with value: -55.00989596857837.
+[I 2025-12-18 02:27:10,994] Trial 11 finished with value: -351.02055561582097 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 4 with value: -55.00989596857837.
+[I 2025-12-18 02:27:14,239] Trial 12 finished with value: -40.721599926032866 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 12 with value: -40.721599926032866.
+[I 2025-12-18 02:27:17,455] Trial 13 finished with value: -250.00541161300893 and parameters: {'embedding_dim': 80, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 12 with value: -40.721599926032866.
+[I 2025-12-18 02:27:20,782] Trial 14 finished with value: -156.58862250248814 and parameters: {'embedding_dim': 101, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 12 with value: -40.721599926032866.
+[I 2025-12-18 02:27:26,110] Trial 15 finished with value: -57.52264409257711 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 12 with value: -40.721599926032866.
+[I 2025-12-18 02:27:29,320] Trial 16 finished with value: -0.5234410698788653 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:27:36,080] Trial 17 finished with value: -35.16891463752862 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:27:42,654] Trial 18 finished with value: -39.93991448086908 and parameters: {'embedding_dim': 99, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:27:49,187] Trial 19 finished with value: -65.91652669200145 and parameters: {'embedding_dim': 105, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:27:55,710] Trial 20 finished with value: -95.68843811313634 and parameters: {'embedding_dim': 91, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:28:02,223] Trial 21 finished with value: -95.67887670868633 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:28:08,714] Trial 22 finished with value: -11.109116132102741 and parameters: {'embedding_dim': 97, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:28:15,216] Trial 23 finished with value: -44.503911887489586 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:28:21,767] Trial 24 finished with value: -57.27543713717792 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:28:26,632] Trial 25 finished with value: -252.05035502793064 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:28:33,318] Trial 26 finished with value: -17.93220629719545 and parameters: {'embedding_dim': 128, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:28:38,242] Trial 27 finished with value: -90.17923985868926 and parameters: {'embedding_dim': 128, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:28:45,013] Trial 28 finished with value: -55.09652726803696 and parameters: {'embedding_dim': 128, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:28:49,927] Trial 29 finished with value: -31.593460543619575 and parameters: {'embedding_dim': 121, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:28:54,891] Trial 30 finished with value: -179.37127859304073 and parameters: {'embedding_dim': 107, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:28:59,904] Trial 31 finished with value: -36.76028440104508 and parameters: {'embedding_dim': 118, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:29:06,632] Trial 32 finished with value: -51.57279025180141 and parameters: {'embedding_dim': 123, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:29:11,651] Trial 33 finished with value: -147.39806344272452 and parameters: {'embedding_dim': 123, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:29:18,367] Trial 34 finished with value: -103.9610918729596 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:29:23,379] Trial 35 finished with value: -75.83469560094974 and parameters: {'embedding_dim': 110, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:29:30,269] Trial 36 finished with value: -163.79613425309753 and parameters: {'embedding_dim': 118, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:29:33,587] Trial 37 finished with value: -186.43029192879297 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:29:38,461] Trial 38 finished with value: -35.42280530123258 and parameters: {'embedding_dim': 125, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:29:45,213] Trial 39 finished with value: -36.747614344844955 and parameters: {'embedding_dim': 91, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:29:48,451] Trial 40 finished with value: -452.84572025613744 and parameters: {'embedding_dim': 110, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:29:54,945] Trial 41 finished with value: -243.1450237464644 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:30:01,456] Trial 42 finished with value: -66.22049762705674 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:30:08,002] Trial 43 finished with value: -101.08376097567876 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:30:14,512] Trial 44 finished with value: -70.0899617597987 and parameters: {'embedding_dim': 120, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:30:21,888] Trial 45 finished with value: -32.01179712130074 and parameters: {'embedding_dim': 115, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:30:27,240] Trial 46 finished with value: -115.1592772974232 and parameters: {'embedding_dim': 115, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:30:30,714] Trial 47 finished with value: -41.601973331690274 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:30:37,916] Trial 48 finished with value: -68.0888532707076 and parameters: {'embedding_dim': 125, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:30:43,291] Trial 49 finished with value: -33.982942831291396 and parameters: {'embedding_dim': 121, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 16 with value: -0.5234410698788653.
+[I 2025-12-18 02:30:47,154] A new study created in memory with name: no-name-19b03b1a-0577-4b38-b709-b325138a9718
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_20000_1_daejeon_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_20000_1_daejeon_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan20000_1_daejeon.csv: Class 0=16137 | Class 1=18721
+Saved ../../data/data_oversampled/ctgan20000/ctgan20000_1_daejeon.csv: Class 0=16137 | Class 1=18721 | Class 2=15441
+Processing ../../data/data_for_modeling/gwangju_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/gwangju_train.csv: Optimizing CTGAN for class 1...
+/opt/conda/envs/py39/lib/python3.9/site-packages/joblib/externals/loky/process_executor.py:752: UserWarning: A worker stopped while some jobs were given to the executor. This can be caused by a too short worker timeout or by a memory leak.
+  warnings.warn(
+[I 2025-12-18 02:31:17,002] Trial 0 finished with value: -631.5219504777826 and parameters: {'embedding_dim': 303, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 0 with value: -631.5219504777826.
+[I 2025-12-18 02:31:40,412] Trial 1 finished with value: -4427.174372149373 and parameters: {'embedding_dim': 183, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -631.5219504777826.
+[I 2025-12-18 02:31:59,984] Trial 2 finished with value: -614.5153792364905 and parameters: {'embedding_dim': 354, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 2 with value: -614.5153792364905.
+[I 2025-12-18 02:33:09,720] Trial 3 finished with value: -1114.5960515846448 and parameters: {'embedding_dim': 343, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 2 with value: -614.5153792364905.
+[I 2025-12-18 02:34:20,187] Trial 4 finished with value: -1330.1267686074527 and parameters: {'embedding_dim': 335, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 2 with value: -614.5153792364905.
+[I 2025-12-18 02:34:28,283] Trial 5 finished with value: -2451.9683913680537 and parameters: {'embedding_dim': 220, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 2 with value: -614.5153792364905.
+[I 2025-12-18 02:34:54,032] Trial 6 finished with value: -517.4226189977754 and parameters: {'embedding_dim': 244, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 6 with value: -517.4226189977754.
+[I 2025-12-18 02:35:08,849] Trial 7 finished with value: -7301.586797028045 and parameters: {'embedding_dim': 188, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 6 with value: -517.4226189977754.
+[I 2025-12-18 02:35:54,700] Trial 8 finished with value: -614.2562396296368 and parameters: {'embedding_dim': 363, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 6 with value: -517.4226189977754.
+[I 2025-12-18 02:36:07,531] Trial 9 finished with value: -323.26488272372416 and parameters: {'embedding_dim': 268, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 9 with value: -323.26488272372416.
+[I 2025-12-18 02:36:22,310] Trial 10 finished with value: -614.8729981394922 and parameters: {'embedding_dim': 481, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 9 with value: -323.26488272372416.
+[I 2025-12-18 02:36:35,212] Trial 11 finished with value: -1526.823207645003 and parameters: {'embedding_dim': 258, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 9 with value: -323.26488272372416.
+[I 2025-12-18 02:37:12,232] Trial 12 finished with value: -36.44621215759166 and parameters: {'embedding_dim': 137, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 12 with value: -36.44621215759166.
+[I 2025-12-18 02:37:23,817] Trial 13 finished with value: -1643.3335528163607 and parameters: {'embedding_dim': 135, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 12 with value: -36.44621215759166.
+[I 2025-12-18 02:38:02,774] Trial 14 finished with value: -476.9704634592466 and parameters: {'embedding_dim': 445, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 12 with value: -36.44621215759166.
+[I 2025-12-18 02:38:45,295] Trial 15 finished with value: -252.06042805295758 and parameters: {'embedding_dim': 134, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 12 with value: -36.44621215759166.
+[I 2025-12-18 02:39:30,119] Trial 16 finished with value: -845.121435251779 and parameters: {'embedding_dim': 132, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 12 with value: -36.44621215759166.
+[I 2025-12-18 02:40:32,380] Trial 17 finished with value: -217.03902536555435 and parameters: {'embedding_dim': 179, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 12 with value: -36.44621215759166.
+[I 2025-12-18 02:41:31,566] Trial 18 finished with value: -1320.3280807523545 and parameters: {'embedding_dim': 186, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 12 with value: -36.44621215759166.
+[I 2025-12-18 02:42:32,755] Trial 19 finished with value: -69.09957088609977 and parameters: {'embedding_dim': 402, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 12 with value: -36.44621215759166.
+[I 2025-12-18 02:43:34,194] Trial 20 finished with value: -441.35400691145185 and parameters: {'embedding_dim': 398, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 12 with value: -36.44621215759166.
+[I 2025-12-18 02:44:36,235] Trial 21 finished with value: -136.85762759188776 and parameters: {'embedding_dim': 420, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 12 with value: -36.44621215759166.
+[I 2025-12-18 02:45:36,319] Trial 22 finished with value: -128.61752984764192 and parameters: {'embedding_dim': 412, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 12 with value: -36.44621215759166.
+[I 2025-12-18 02:46:25,254] Trial 23 finished with value: -471.3776713426056 and parameters: {'embedding_dim': 511, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 12 with value: -36.44621215759166.
+[I 2025-12-18 02:47:28,674] Trial 24 finished with value: -613.0786223642757 and parameters: {'embedding_dim': 388, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 12 with value: -36.44621215759166.
+[I 2025-12-18 02:48:11,825] Trial 25 finished with value: -149.4065647720761 and parameters: {'embedding_dim': 446, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 12 with value: -36.44621215759166.
+[I 2025-12-18 02:49:00,077] Trial 26 finished with value: -1736.9118572176435 and parameters: {'embedding_dim': 309, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 12 with value: -36.44621215759166.
+[I 2025-12-18 02:50:02,165] Trial 27 finished with value: -189.33361936853203 and parameters: {'embedding_dim': 380, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 12 with value: -36.44621215759166.
+[I 2025-12-18 02:50:49,292] Trial 28 finished with value: -323.4872092357198 and parameters: {'embedding_dim': 437, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 12 with value: -36.44621215759166.
+[I 2025-12-18 02:51:20,681] Trial 29 finished with value: -1330.734197700448 and parameters: {'embedding_dim': 477, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 12 with value: -36.44621215759166.
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_20000_1_gwangju_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_20000_1_gwangju_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan20000_1_gwangju.csv: Class 0=17013 | Class 1=19189
+Saved ../../data/data_oversampled/ctgan20000/ctgan20000_1_gwangju.csv: Class 0=17013 | Class 1=19189 | Class 2=15692
+
+Running ctgan_sample_20000_2.py...
+[I 2025-12-18 02:52:00,084] A new study created in memory with name: no-name-4da39461-c0a2-4a0c-8c30-939f9d3d2736
+[I 2025-12-18 02:52:11,107] Trial 0 finished with value: -9.931443087127949 and parameters: {'embedding_dim': 123, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -9.931443087127949.
+[I 2025-12-18 02:52:17,791] Trial 1 finished with value: -0.6974710927943178 and parameters: {'embedding_dim': 104, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:52:26,088] Trial 2 finished with value: -47.365687299461165 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:52:40,838] Trial 3 finished with value: -2.690373874174016 and parameters: {'embedding_dim': 116, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:52:51,020] Trial 4 finished with value: -46.946690192258174 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:53:07,340] Trial 5 finished with value: -25.39503840259801 and parameters: {'embedding_dim': 117, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:53:20,868] Trial 6 finished with value: -56.89515999350815 and parameters: {'embedding_dim': 99, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:53:35,668] Trial 7 finished with value: -104.79732857626384 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:53:58,695] Trial 8 finished with value: -173.99577503082443 and parameters: {'embedding_dim': 85, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:54:09,004] Trial 9 finished with value: -100.31646733119463 and parameters: {'embedding_dim': 115, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:54:15,625] Trial 10 finished with value: -2.1301101960397393 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:54:22,218] Trial 11 finished with value: -1.7875583974853806 and parameters: {'embedding_dim': 100, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:54:28,901] Trial 12 finished with value: -7.260034809745777 and parameters: {'embedding_dim': 105, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:54:35,517] Trial 13 finished with value: -62.52217667735287 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:54:42,340] Trial 14 finished with value: -105.36672492207754 and parameters: {'embedding_dim': 107, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:54:47,198] Trial 15 finished with value: -2.2028720414335035 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:54:59,008] Trial 16 finished with value: -136.21980381110677 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:55:05,658] Trial 17 finished with value: -303.360601340668 and parameters: {'embedding_dim': 128, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:55:11,494] Trial 18 finished with value: -159.06083370344479 and parameters: {'embedding_dim': 110, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:55:26,351] Trial 19 finished with value: -30.581129570155216 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:55:32,956] Trial 20 finished with value: -75.01855117519126 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:55:39,561] Trial 21 finished with value: -1.2899831698174062 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:55:46,139] Trial 22 finished with value: -236.03897566621774 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:55:52,758] Trial 23 finished with value: -65.68855319347206 and parameters: {'embedding_dim': 109, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:55:59,368] Trial 24 finished with value: -115.9236638025478 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:56:09,421] Trial 25 finished with value: -66.47260602740927 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:56:16,040] Trial 26 finished with value: -199.94724592083855 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:56:22,709] Trial 27 finished with value: -84.57102463143801 and parameters: {'embedding_dim': 104, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:56:28,545] Trial 28 finished with value: -1.6309559449618631 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:56:36,239] Trial 29 finished with value: -3.5301091546370347 and parameters: {'embedding_dim': 91, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:56:42,080] Trial 30 finished with value: -151.92414631781358 and parameters: {'embedding_dim': 123, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:56:47,841] Trial 31 finished with value: -145.13336722044397 and parameters: {'embedding_dim': 100, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:56:53,654] Trial 32 finished with value: -194.37494580678188 and parameters: {'embedding_dim': 99, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:56:57,605] Trial 33 finished with value: -200.96730060536044 and parameters: {'embedding_dim': 88, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:57:20,604] Trial 34 finished with value: -61.509330411875766 and parameters: {'embedding_dim': 112, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:57:27,256] Trial 35 finished with value: -3.0084376471754983 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:57:40,890] Trial 36 finished with value: -188.16016751069586 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:57:44,950] Trial 37 finished with value: -52.15955603675911 and parameters: {'embedding_dim': 105, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:58:08,027] Trial 38 finished with value: -53.231776178417284 and parameters: {'embedding_dim': 114, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:58:21,855] Trial 39 finished with value: -125.05563216306962 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:58:28,532] Trial 40 finished with value: -16.230096497575992 and parameters: {'embedding_dim': 118, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:58:35,133] Trial 41 finished with value: -63.187445098925586 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -0.6974710927943178.
+[I 2025-12-18 02:58:41,792] Trial 42 finished with value: -0.1341231922104282 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 42 with value: -0.1341231922104282.
+[I 2025-12-18 02:58:48,448] Trial 43 finished with value: -54.298825857199446 and parameters: {'embedding_dim': 107, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 42 with value: -0.1341231922104282.
+[I 2025-12-18 02:58:55,089] Trial 44 finished with value: -6.6212776929646955 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 42 with value: -0.1341231922104282.
+[I 2025-12-18 02:59:09,801] Trial 45 finished with value: -50.69515936856901 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 42 with value: -0.1341231922104282.
+[I 2025-12-18 02:59:16,332] Trial 46 finished with value: -30.880786038689834 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 42 with value: -0.1341231922104282.
+[I 2025-12-18 02:59:22,934] Trial 47 finished with value: -7.513109809540677 and parameters: {'embedding_dim': 107, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 42 with value: -0.1341231922104282.
+[I 2025-12-18 02:59:28,707] Trial 48 finished with value: -24.471309165108718 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 42 with value: -0.1341231922104282.
+[I 2025-12-18 02:59:35,305] Trial 49 finished with value: -262.17307831093393 and parameters: {'embedding_dim': 100, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 42 with value: -0.1341231922104282.
+[I 2025-12-18 02:59:42,266] A new study created in memory with name: no-name-937c372a-d784-42f5-a888-b504998b793e
+Using device: cuda
+Processing ../../data/data_for_modeling/incheon_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/incheon_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-18 03:01:10,355] Trial 0 finished with value: -255.00601129165102 and parameters: {'embedding_dim': 501, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 0 with value: -255.00601129165102.
+[I 2025-12-18 03:01:41,428] Trial 1 finished with value: -137.3655005393645 and parameters: {'embedding_dim': 133, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 1 with value: -137.3655005393645.
+[I 2025-12-18 03:02:06,641] Trial 2 finished with value: -382.4334072377357 and parameters: {'embedding_dim': 290, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 1 with value: -137.3655005393645.
+[I 2025-12-18 03:02:20,169] Trial 3 finished with value: -2160.541704565202 and parameters: {'embedding_dim': 296, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 1 with value: -137.3655005393645.
+[I 2025-12-18 03:03:15,644] Trial 4 finished with value: -706.5314881750098 and parameters: {'embedding_dim': 275, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 1 with value: -137.3655005393645.
+[I 2025-12-18 03:03:46,178] Trial 5 finished with value: -666.0279445898708 and parameters: {'embedding_dim': 498, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 1 with value: -137.3655005393645.
+[I 2025-12-18 03:04:05,448] Trial 6 finished with value: -294.60907260234995 and parameters: {'embedding_dim': 369, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 1 with value: -137.3655005393645.
+[I 2025-12-18 03:04:33,020] Trial 7 finished with value: -839.885218414725 and parameters: {'embedding_dim': 478, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 1 with value: -137.3655005393645.
+[I 2025-12-18 03:04:46,986] Trial 8 finished with value: -2071.8765254558584 and parameters: {'embedding_dim': 304, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 1 with value: -137.3655005393645.
+[I 2025-12-18 03:06:27,876] Trial 9 finished with value: -9.655857298407833 and parameters: {'embedding_dim': 229, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 9 with value: -9.655857298407833.
+[I 2025-12-18 03:08:09,365] Trial 10 finished with value: -183.70061402135022 and parameters: {'embedding_dim': 176, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 9 with value: -9.655857298407833.
+[I 2025-12-18 03:09:34,419] Trial 11 finished with value: -6.234290569758299 and parameters: {'embedding_dim': 128, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 11 with value: -6.234290569758299.
+[I 2025-12-18 03:11:16,263] Trial 12 finished with value: -617.7932212232616 and parameters: {'embedding_dim': 210, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 11 with value: -6.234290569758299.
+[I 2025-12-18 03:12:40,830] Trial 13 finished with value: -460.3126617653509 and parameters: {'embedding_dim': 224, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 11 with value: -6.234290569758299.
+[I 2025-12-18 03:13:47,951] Trial 14 finished with value: -4.155793338722654 and parameters: {'embedding_dim': 130, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -4.155793338722654.
+[I 2025-12-18 03:14:55,640] Trial 15 finished with value: -1774.6650586355006 and parameters: {'embedding_dim': 130, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -4.155793338722654.
+[I 2025-12-18 03:15:45,976] Trial 16 finished with value: -1015.5358825377994 and parameters: {'embedding_dim': 389, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -4.155793338722654.
+[I 2025-12-18 03:16:53,473] Trial 17 finished with value: -42.05338559672762 and parameters: {'embedding_dim': 168, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -4.155793338722654.
+[I 2025-12-18 03:17:29,492] Trial 18 finished with value: -544.2345923424307 and parameters: {'embedding_dim': 184, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 14 with value: -4.155793338722654.
+[I 2025-12-18 03:18:54,256] Trial 19 finished with value: -128.29877197339817 and parameters: {'embedding_dim': 363, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 14 with value: -4.155793338722654.
+[I 2025-12-18 03:19:44,631] Trial 20 finished with value: -144.37539476817545 and parameters: {'embedding_dim': 250, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -4.155793338722654.
+[I 2025-12-18 03:21:31,133] Trial 21 finished with value: -778.1905880585 and parameters: {'embedding_dim': 129, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 14 with value: -4.155793338722654.
+[I 2025-12-18 03:23:01,425] Trial 22 finished with value: -4.216595674158768 and parameters: {'embedding_dim': 219, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 14 with value: -4.155793338722654.
+[I 2025-12-18 03:24:31,637] Trial 23 finished with value: -826.0641418924965 and parameters: {'embedding_dim': 165, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 14 with value: -4.155793338722654.
+[I 2025-12-18 03:25:42,033] Trial 24 finished with value: -2619.9659388668524 and parameters: {'embedding_dim': 193, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -4.155793338722654.
+[I 2025-12-18 03:26:30,925] Trial 25 finished with value: -3117.2478714709596 and parameters: {'embedding_dim': 256, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 14 with value: -4.155793338722654.
+[I 2025-12-18 03:27:42,327] Trial 26 finished with value: -33.545885708366114 and parameters: {'embedding_dim': 164, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -4.155793338722654.
+[I 2025-12-18 03:29:11,952] Trial 27 finished with value: -447.02543312053155 and parameters: {'embedding_dim': 208, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 14 with value: -4.155793338722654.
+[I 2025-12-18 03:30:38,511] Trial 28 finished with value: -55.73450485561443 and parameters: {'embedding_dim': 149, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 14 with value: -4.155793338722654.
+[I 2025-12-18 03:31:48,367] Trial 29 finished with value: -22.38751062699729 and parameters: {'embedding_dim': 240, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -4.155793338722654.
+[I 2025-12-18 03:32:58,179] A new study created in memory with name: no-name-29f51c28-bb36-4103-8399-069f4dbf3242
+[I 2025-12-18 03:33:01,340] Trial 0 finished with value: -301.2540139558903 and parameters: {'embedding_dim': 74, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -301.2540139558903.
+[I 2025-12-18 03:33:06,204] Trial 1 finished with value: -17.209973892563312 and parameters: {'embedding_dim': 109, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -17.209973892563312.
+[I 2025-12-18 03:33:13,435] Trial 2 finished with value: -28.71200439534447 and parameters: {'embedding_dim': 66, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -17.209973892563312.
+[I 2025-12-18 03:33:18,458] Trial 3 finished with value: -67.76236925412145 and parameters: {'embedding_dim': 99, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -17.209973892563312.
+[I 2025-12-18 03:33:25,046] Trial 4 finished with value: -26.782411048513154 and parameters: {'embedding_dim': 123, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 1 with value: -17.209973892563312.
+[I 2025-12-18 03:33:28,325] Trial 5 finished with value: -170.86082426134527 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 1 with value: -17.209973892563312.
+[I 2025-12-18 03:33:33,068] Trial 6 finished with value: -14.534908214765343 and parameters: {'embedding_dim': 115, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 6 with value: -14.534908214765343.
+[I 2025-12-18 03:33:40,255] Trial 7 finished with value: -87.22957376200802 and parameters: {'embedding_dim': 86, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 6 with value: -14.534908214765343.
+[I 2025-12-18 03:33:44,808] Trial 8 finished with value: -23.375399242657416 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 6 with value: -14.534908214765343.
+[I 2025-12-18 03:33:49,600] Trial 9 finished with value: -73.18730361190514 and parameters: {'embedding_dim': 108, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 6 with value: -14.534908214765343.
+[I 2025-12-18 03:33:54,598] Trial 10 finished with value: -35.67338132627458 and parameters: {'embedding_dim': 127, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 6 with value: -14.534908214765343.
+[I 2025-12-18 03:33:59,381] Trial 11 finished with value: -13.023499840071866 and parameters: {'embedding_dim': 112, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 11 with value: -13.023499840071866.
+[I 2025-12-18 03:34:04,139] Trial 12 finished with value: -65.5154056879374 and parameters: {'embedding_dim': 115, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 11 with value: -13.023499840071866.
+[I 2025-12-18 03:34:08,924] Trial 13 finished with value: -66.70059146144095 and parameters: {'embedding_dim': 117, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 11 with value: -13.023499840071866.
+[I 2025-12-18 03:34:15,232] Trial 14 finished with value: -14.119666086080194 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 11 with value: -13.023499840071866.
+[I 2025-12-18 03:34:22,491] Trial 15 finished with value: -3.941506401847286 and parameters: {'embedding_dim': 100, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:34:29,579] Trial 16 finished with value: -29.87131840600784 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:34:36,761] Trial 17 finished with value: -5.598982241891541 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:34:45,519] Trial 18 finished with value: -36.42400032974652 and parameters: {'embedding_dim': 86, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:34:53,886] Trial 19 finished with value: -16.867828214360273 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:35:01,028] Trial 20 finished with value: -28.672346748356 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:35:08,204] Trial 21 finished with value: -12.79103841313695 and parameters: {'embedding_dim': 109, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:35:15,399] Trial 22 finished with value: -47.07295923765333 and parameters: {'embedding_dim': 104, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:35:22,527] Trial 23 finished with value: -11.59687962817118 and parameters: {'embedding_dim': 120, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:35:29,725] Trial 24 finished with value: -8.623538831416859 and parameters: {'embedding_dim': 124, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:35:36,923] Trial 25 finished with value: -250.70707052491787 and parameters: {'embedding_dim': 126, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:35:44,118] Trial 26 finished with value: -93.34785774140131 and parameters: {'embedding_dim': 88, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:35:52,861] Trial 27 finished with value: -7.011152539844073 and parameters: {'embedding_dim': 81, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:36:00,051] Trial 28 finished with value: -9.783632600206817 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:36:03,335] Trial 29 finished with value: -212.52279350451667 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:36:10,566] Trial 30 finished with value: -44.26891648100756 and parameters: {'embedding_dim': 69, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:36:17,792] Trial 31 finished with value: -34.85467090821998 and parameters: {'embedding_dim': 99, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:36:24,922] Trial 32 finished with value: -47.2310630827432 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:36:32,272] Trial 33 finished with value: -28.857616375593118 and parameters: {'embedding_dim': 69, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:36:39,412] Trial 34 finished with value: -16.985991577380723 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:36:46,556] Trial 35 finished with value: -15.7518431478514 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:36:51,516] Trial 36 finished with value: -20.91432086415192 and parameters: {'embedding_dim': 105, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:36:59,101] Trial 37 finished with value: -54.56414495946836 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:37:06,992] Trial 38 finished with value: -116.24501370530405 and parameters: {'embedding_dim': 122, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:37:14,274] Trial 39 finished with value: -13.846924021334985 and parameters: {'embedding_dim': 83, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:37:19,306] Trial 40 finished with value: -65.47983718909622 and parameters: {'embedding_dim': 71, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:37:26,541] Trial 41 finished with value: -20.490612330636054 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:37:33,719] Trial 42 finished with value: -36.21153598066285 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:37:40,892] Trial 43 finished with value: -39.243248512871496 and parameters: {'embedding_dim': 71, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 15 with value: -3.941506401847286.
+[I 2025-12-18 03:37:48,079] Trial 44 finished with value: -1.3676171608182663 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 44 with value: -1.3676171608182663.
+[I 2025-12-18 03:37:55,266] Trial 45 finished with value: -19.251355904206555 and parameters: {'embedding_dim': 89, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 44 with value: -1.3676171608182663.
+[I 2025-12-18 03:38:04,136] Trial 46 finished with value: -4.322891021670951 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 44 with value: -1.3676171608182663.
+[I 2025-12-18 03:38:09,723] Trial 47 finished with value: -55.54183576864136 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 44 with value: -1.3676171608182663.
+[I 2025-12-18 03:38:17,176] Trial 48 finished with value: -61.264198180918314 and parameters: {'embedding_dim': 85, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 44 with value: -1.3676171608182663.
+[I 2025-12-18 03:38:20,830] Trial 49 finished with value: -350.6843669349727 and parameters: {'embedding_dim': 101, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 44 with value: -1.3676171608182663.
+[I 2025-12-18 03:38:28,366] A new study created in memory with name: no-name-b306c49f-aa63-4bf2-9151-3fbbe33e4113
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_20000_2_incheon_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_20000_2_incheon_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan20000_2_incheon.csv: Class 0=18501 | Class 1=16898
+Saved ../../data/data_oversampled/ctgan20000/ctgan20000_2_incheon.csv: Class 0=18863 | Class 1=19443 | Class 2=14637
+Processing ../../data/data_for_modeling/seoul_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/seoul_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-18 03:38:39,240] Trial 0 finished with value: -2347.5052639026476 and parameters: {'embedding_dim': 269, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 0 with value: -2347.5052639026476.
+[I 2025-12-18 03:39:15,055] Trial 1 finished with value: -909.653930797797 and parameters: {'embedding_dim': 128, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -909.653930797797.
+[I 2025-12-18 03:39:27,202] Trial 2 finished with value: -204.45581099216759 and parameters: {'embedding_dim': 147, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 2 with value: -204.45581099216759.
+[I 2025-12-18 03:40:01,936] Trial 3 finished with value: -299.80521304565264 and parameters: {'embedding_dim': 384, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 2 with value: -204.45581099216759.
+[I 2025-12-18 03:40:45,264] Trial 4 finished with value: -165.95209935637357 and parameters: {'embedding_dim': 427, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 4 with value: -165.95209935637357.
+[I 2025-12-18 03:41:00,038] Trial 5 finished with value: -314.82311517142335 and parameters: {'embedding_dim': 403, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 4 with value: -165.95209935637357.
+[I 2025-12-18 03:41:42,838] Trial 6 finished with value: -386.41169084341607 and parameters: {'embedding_dim': 223, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 4 with value: -165.95209935637357.
+[I 2025-12-18 03:42:19,598] Trial 7 finished with value: -72.27512030084144 and parameters: {'embedding_dim': 365, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 7 with value: -72.27512030084144.
+[I 2025-12-18 03:43:07,132] Trial 8 finished with value: -1489.8450722014265 and parameters: {'embedding_dim': 261, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 7 with value: -72.27512030084144.
+[I 2025-12-18 03:44:06,622] Trial 9 finished with value: -18.126639848601144 and parameters: {'embedding_dim': 259, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 9 with value: -18.126639848601144.
+[I 2025-12-18 03:45:04,266] Trial 10 finished with value: -290.4772252371706 and parameters: {'embedding_dim': 503, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 9 with value: -18.126639848601144.
+[I 2025-12-18 03:46:01,470] Trial 11 finished with value: -308.7718207667961 and parameters: {'embedding_dim': 338, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 9 with value: -18.126639848601144.
+[I 2025-12-18 03:46:29,239] Trial 12 finished with value: -555.4229360694122 and parameters: {'embedding_dim': 316, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 9 with value: -18.126639848601144.
+[I 2025-12-18 03:47:26,532] Trial 13 finished with value: -142.51050125047337 and parameters: {'embedding_dim': 206, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 9 with value: -18.126639848601144.
+[I 2025-12-18 03:47:46,337] Trial 14 finished with value: -293.4605614806872 and parameters: {'embedding_dim': 329, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 9 with value: -18.126639848601144.
+[I 2025-12-18 03:48:14,001] Trial 15 finished with value: -20.173872876592245 and parameters: {'embedding_dim': 464, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 9 with value: -18.126639848601144.
+[I 2025-12-18 03:48:48,517] Trial 16 finished with value: -46.10220462718365 and parameters: {'embedding_dim': 505, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 9 with value: -18.126639848601144.
+[I 2025-12-18 03:49:35,068] Trial 17 finished with value: -960.8107081371776 and parameters: {'embedding_dim': 452, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 9 with value: -18.126639848601144.
+[I 2025-12-18 03:50:03,172] Trial 18 finished with value: -16.31202582078589 and parameters: {'embedding_dim': 287, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 18 with value: -16.31202582078589.
+[I 2025-12-18 03:50:14,360] Trial 19 finished with value: -194.7554025334868 and parameters: {'embedding_dim': 277, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 18 with value: -16.31202582078589.
+[I 2025-12-18 03:51:01,449] Trial 20 finished with value: -332.1338682591602 and parameters: {'embedding_dim': 190, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 18 with value: -16.31202582078589.
+[I 2025-12-18 03:51:29,635] Trial 21 finished with value: -420.8901092613109 and parameters: {'embedding_dim': 292, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 18 with value: -16.31202582078589.
+[I 2025-12-18 03:51:58,854] Trial 22 finished with value: -751.2139101030245 and parameters: {'embedding_dim': 243, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 18 with value: -16.31202582078589.
+[I 2025-12-18 03:52:33,837] Trial 23 finished with value: -70.26713952929454 and parameters: {'embedding_dim': 189, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 18 with value: -16.31202582078589.
+[I 2025-12-18 03:53:02,938] Trial 24 finished with value: -232.46334592134355 and parameters: {'embedding_dim': 306, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 18 with value: -16.31202582078589.
+[I 2025-12-18 03:53:25,054] Trial 25 finished with value: -93.46903527411708 and parameters: {'embedding_dim': 346, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 18 with value: -16.31202582078589.
+[I 2025-12-18 03:54:00,050] Trial 26 finished with value: -88.00282025719703 and parameters: {'embedding_dim': 448, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 18 with value: -16.31202582078589.
+[I 2025-12-18 03:54:29,253] Trial 27 finished with value: -79.96054393961322 and parameters: {'embedding_dim': 238, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 18 with value: -16.31202582078589.
+[I 2025-12-18 03:54:48,884] Trial 28 finished with value: -408.88569010229725 and parameters: {'embedding_dim': 476, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 18 with value: -16.31202582078589.
+[I 2025-12-18 03:55:45,240] Trial 29 finished with value: -599.4705615609688 and parameters: {'embedding_dim': 273, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 18 with value: -16.31202582078589.
+[I 2025-12-18 03:56:15,241] A new study created in memory with name: no-name-6c3126e8-dee9-4546-862a-4796736fc658
+[I 2025-12-18 03:56:18,618] Trial 0 finished with value: -34.074749813191225 and parameters: {'embedding_dim': 70, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 0 with value: -34.074749813191225.
+[I 2025-12-18 03:56:23,536] Trial 1 finished with value: -19.85583754412651 and parameters: {'embedding_dim': 72, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -19.85583754412651.
+[I 2025-12-18 03:56:30,367] Trial 2 finished with value: -38.234833713418794 and parameters: {'embedding_dim': 88, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 1 with value: -19.85583754412651.
+[I 2025-12-18 03:56:35,471] Trial 3 finished with value: -40.43166359928276 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -19.85583754412651.
+[I 2025-12-18 03:56:39,115] Trial 4 finished with value: -47.31956257767959 and parameters: {'embedding_dim': 72, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 1 with value: -19.85583754412651.
+[I 2025-12-18 03:56:46,352] Trial 5 finished with value: -14.834715274063605 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:56:49,573] Trial 6 finished with value: -36.442592459070504 and parameters: {'embedding_dim': 81, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:56:56,390] Trial 7 finished with value: -38.9922295540233 and parameters: {'embedding_dim': 103, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:57:01,325] Trial 8 finished with value: -21.562189055897935 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:57:04,683] Trial 9 finished with value: -259.8317176723574 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:57:12,110] Trial 10 finished with value: -35.2410057048043 and parameters: {'embedding_dim': 128, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:57:17,184] Trial 11 finished with value: -18.239284078610698 and parameters: {'embedding_dim': 118, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:57:24,749] Trial 12 finished with value: -46.12828558797065 and parameters: {'embedding_dim': 118, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:57:30,288] Trial 13 finished with value: -45.610989956009135 and parameters: {'embedding_dim': 116, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:57:35,281] Trial 14 finished with value: -66.03985257453945 and parameters: {'embedding_dim': 127, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:57:42,710] Trial 15 finished with value: -73.48551426609046 and parameters: {'embedding_dim': 107, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:57:47,658] Trial 16 finished with value: -86.22338523640059 and parameters: {'embedding_dim': 118, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:57:54,276] Trial 17 finished with value: -40.00073491958905 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:57:59,687] Trial 18 finished with value: -22.974537992877625 and parameters: {'embedding_dim': 110, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:58:06,253] Trial 19 finished with value: -38.64035859258341 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:58:11,755] Trial 20 finished with value: -19.28454190930487 and parameters: {'embedding_dim': 122, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:58:17,272] Trial 21 finished with value: -63.98841330397171 and parameters: {'embedding_dim': 122, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:58:22,780] Trial 22 finished with value: -50.04581722159641 and parameters: {'embedding_dim': 114, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:58:28,291] Trial 23 finished with value: -104.61810296631475 and parameters: {'embedding_dim': 122, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:58:33,726] Trial 24 finished with value: -37.38836650022116 and parameters: {'embedding_dim': 104, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:58:37,234] Trial 25 finished with value: -25.2377084876165 and parameters: {'embedding_dim': 123, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:58:43,821] Trial 26 finished with value: -94.05383203378432 and parameters: {'embedding_dim': 110, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:58:49,199] Trial 27 finished with value: -21.833206901363596 and parameters: {'embedding_dim': 99, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:58:56,469] Trial 28 finished with value: -74.05368659888764 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:58:59,749] Trial 29 finished with value: -82.36251019814209 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 5 with value: -14.834715274063605.
+[I 2025-12-18 03:59:04,863] Trial 30 finished with value: -13.558329404341405 and parameters: {'embedding_dim': 124, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 30 with value: -13.558329404341405.
+[I 2025-12-18 03:59:09,967] Trial 31 finished with value: -33.441796846924966 and parameters: {'embedding_dim': 125, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 30 with value: -13.558329404341405.
+[I 2025-12-18 03:59:15,211] Trial 32 finished with value: -130.37095635165937 and parameters: {'embedding_dim': 119, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 30 with value: -13.558329404341405.
+[I 2025-12-18 03:59:20,274] Trial 33 finished with value: -80.05862628618557 and parameters: {'embedding_dim': 113, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 30 with value: -13.558329404341405.
+[I 2025-12-18 03:59:25,294] Trial 34 finished with value: -15.278750038588493 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 30 with value: -13.558329404341405.
+[I 2025-12-18 03:59:30,385] Trial 35 finished with value: -0.252565142187313 and parameters: {'embedding_dim': 65, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 35 with value: -0.252565142187313.
+[I 2025-12-18 03:59:35,456] Trial 36 finished with value: -18.48960861316448 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 35 with value: -0.252565142187313.
+[I 2025-12-18 03:59:38,792] Trial 37 finished with value: -20.84452170657722 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 35 with value: -0.252565142187313.
+[I 2025-12-18 03:59:43,858] Trial 38 finished with value: -5.412304644469729 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 35 with value: -0.252565142187313.
+[I 2025-12-18 03:59:47,229] Trial 39 finished with value: -0.22680090701944386 and parameters: {'embedding_dim': 74, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 39 with value: -0.22680090701944386.
+[I 2025-12-18 03:59:50,583] Trial 40 finished with value: -205.49864340089448 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 39 with value: -0.22680090701944386.
+[I 2025-12-18 03:59:53,969] Trial 41 finished with value: -17.876482280075837 and parameters: {'embedding_dim': 75, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 39 with value: -0.22680090701944386.
+[I 2025-12-18 03:59:57,317] Trial 42 finished with value: -11.823293085096035 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 39 with value: -0.22680090701944386.
+[I 2025-12-18 04:00:00,662] Trial 43 finished with value: -264.0025896793565 and parameters: {'embedding_dim': 68, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 39 with value: -0.22680090701944386.
+[I 2025-12-18 04:00:04,004] Trial 44 finished with value: -123.96341576601424 and parameters: {'embedding_dim': 73, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 39 with value: -0.22680090701944386.
+[I 2025-12-18 04:00:07,351] Trial 45 finished with value: -11.050983289423126 and parameters: {'embedding_dim': 83, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 39 with value: -0.22680090701944386.
+[I 2025-12-18 04:00:10,700] Trial 46 finished with value: -4.611823148222482 and parameters: {'embedding_dim': 83, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 39 with value: -0.22680090701944386.
+[I 2025-12-18 04:00:14,044] Trial 47 finished with value: -47.81253166430675 and parameters: {'embedding_dim': 83, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 39 with value: -0.22680090701944386.
+[I 2025-12-18 04:00:17,390] Trial 48 finished with value: -117.96048409396928 and parameters: {'embedding_dim': 77, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 39 with value: -0.22680090701944386.
+[I 2025-12-18 04:00:20,767] Trial 49 finished with value: -11.371525172813996 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 39 with value: -0.22680090701944386.
+[I 2025-12-18 04:00:24,458] A new study created in memory with name: no-name-1cc9074b-e39b-48c1-b1e4-314879f7b294
+[I 2025-12-18 04:00:34,789] Trial 0 finished with value: -447.50384331987215 and parameters: {'embedding_dim': 149, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 0 with value: -447.50384331987215.
+[I 2025-12-18 04:00:46,693] Trial 1 finished with value: -4721.941641153421 and parameters: {'embedding_dim': 347, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -447.50384331987215.
+[I 2025-12-18 04:01:00,162] Trial 2 finished with value: -752.0996754648274 and parameters: {'embedding_dim': 466, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 0 with value: -447.50384331987215.
+[I 2025-12-18 04:01:18,289] Trial 3 finished with value: -568.5592498881099 and parameters: {'embedding_dim': 334, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 0 with value: -447.50384331987215.
+[I 2025-12-18 04:01:28,606] Trial 4 finished with value: -2328.347402320343 and parameters: {'embedding_dim': 394, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 0 with value: -447.50384331987215.
+[I 2025-12-18 04:01:49,982] Trial 5 finished with value: -965.9855481641217 and parameters: {'embedding_dim': 302, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -447.50384331987215.
+[I 2025-12-18 04:02:02,720] Trial 6 finished with value: -1095.1759628830132 and parameters: {'embedding_dim': 197, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -447.50384331987215.
+[I 2025-12-18 04:02:20,022] Trial 7 finished with value: -691.4738960174803 and parameters: {'embedding_dim': 438, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -447.50384331987215.
+[I 2025-12-18 04:02:34,056] Trial 8 finished with value: -286.8012455277949 and parameters: {'embedding_dim': 138, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 8 with value: -286.8012455277949.
+[I 2025-12-18 04:02:47,952] Trial 9 finished with value: -2226.575930863456 and parameters: {'embedding_dim': 187, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 8 with value: -286.8012455277949.
+[I 2025-12-18 04:03:03,743] Trial 10 finished with value: -1874.2936583045084 and parameters: {'embedding_dim': 266, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 8 with value: -286.8012455277949.
+[I 2025-12-18 04:03:19,334] Trial 11 finished with value: -536.5753383490564 and parameters: {'embedding_dim': 138, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 8 with value: -286.8012455277949.
+[I 2025-12-18 04:03:36,517] Trial 12 finished with value: -594.7305632404725 and parameters: {'embedding_dim': 129, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 8 with value: -286.8012455277949.
+[I 2025-12-18 04:03:49,526] Trial 13 finished with value: -302.2930891909734 and parameters: {'embedding_dim': 219, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 8 with value: -286.8012455277949.
+[I 2025-12-18 04:04:03,188] Trial 14 finished with value: -782.0802894818295 and parameters: {'embedding_dim': 234, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 8 with value: -286.8012455277949.
+[I 2025-12-18 04:04:20,044] Trial 15 finished with value: -2324.137787837769 and parameters: {'embedding_dim': 215, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 8 with value: -286.8012455277949.
+[I 2025-12-18 04:04:29,527] Trial 16 finished with value: -572.5203425611694 and parameters: {'embedding_dim': 270, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 8 with value: -286.8012455277949.
+[I 2025-12-18 04:04:43,495] Trial 17 finished with value: -1432.9557284506238 and parameters: {'embedding_dim': 177, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 8 with value: -286.8012455277949.
+[I 2025-12-18 04:04:51,685] Trial 18 finished with value: -1767.5627279787723 and parameters: {'embedding_dim': 246, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 8 with value: -286.8012455277949.
+[I 2025-12-18 04:05:01,809] Trial 19 finished with value: -2842.4599497472145 and parameters: {'embedding_dim': 171, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 8 with value: -286.8012455277949.
+[I 2025-12-18 04:05:15,930] Trial 20 finished with value: -1021.3037225865041 and parameters: {'embedding_dim': 292, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 8 with value: -286.8012455277949.
+[I 2025-12-18 04:05:27,321] Trial 21 finished with value: -501.48830892041974 and parameters: {'embedding_dim': 151, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 8 with value: -286.8012455277949.
+[I 2025-12-18 04:05:37,591] Trial 22 finished with value: -739.4947981548385 and parameters: {'embedding_dim': 214, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 8 with value: -286.8012455277949.
+[I 2025-12-18 04:05:50,244] Trial 23 finished with value: -959.7841801750293 and parameters: {'embedding_dim': 160, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 8 with value: -286.8012455277949.
+[I 2025-12-18 04:05:59,782] Trial 24 finished with value: -12385.495197858912 and parameters: {'embedding_dim': 137, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 8 with value: -286.8012455277949.
+[I 2025-12-18 04:06:09,794] Trial 25 finished with value: -1023.5859313082914 and parameters: {'embedding_dim': 208, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 8 with value: -286.8012455277949.
+[I 2025-12-18 04:06:20,280] Trial 26 finished with value: -1852.534970167409 and parameters: {'embedding_dim': 170, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 8 with value: -286.8012455277949.
+[I 2025-12-18 04:06:33,167] Trial 27 finished with value: -343.47485064481185 and parameters: {'embedding_dim': 239, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 8 with value: -286.8012455277949.
+[I 2025-12-18 04:06:47,071] Trial 28 finished with value: -566.1005181519185 and parameters: {'embedding_dim': 363, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 8 with value: -286.8012455277949.
+[I 2025-12-18 04:06:59,943] Trial 29 finished with value: -1870.9411541571421 and parameters: {'embedding_dim': 242, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 8 with value: -286.8012455277949.
+[I 2025-12-18 04:07:12,796] A new study created in memory with name: no-name-f982243c-196e-4d84-9ff7-2fc6cb2d8c98
+[I 2025-12-18 04:07:15,951] Trial 0 finished with value: -54.776087752773456 and parameters: {'embedding_dim': 115, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -54.776087752773456.
+[I 2025-12-18 04:07:19,352] Trial 1 finished with value: -98.15280984439438 and parameters: {'embedding_dim': 91, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -54.776087752773456.
+[I 2025-12-18 04:07:26,064] Trial 2 finished with value: -29.038973616682487 and parameters: {'embedding_dim': 71, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -29.038973616682487.
+[I 2025-12-18 04:07:32,814] Trial 3 finished with value: -53.115697238651194 and parameters: {'embedding_dim': 125, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -29.038973616682487.
+[I 2025-12-18 04:07:39,978] Trial 4 finished with value: -131.64592170762697 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -29.038973616682487.
+[I 2025-12-18 04:07:43,343] Trial 5 finished with value: -33.47390516670987 and parameters: {'embedding_dim': 66, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -29.038973616682487.
+[I 2025-12-18 04:07:48,054] Trial 6 finished with value: -38.68804381125939 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -29.038973616682487.
+[I 2025-12-18 04:07:52,784] Trial 7 finished with value: -33.69311529889087 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -29.038973616682487.
+[I 2025-12-18 04:07:59,116] Trial 8 finished with value: -4.084881450725948 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:08:05,625] Trial 9 finished with value: -97.40594913731584 and parameters: {'embedding_dim': 105, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:08:11,983] Trial 10 finished with value: -60.66294416571748 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:08:16,922] Trial 11 finished with value: -9.386632902824388 and parameters: {'embedding_dim': 66, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:08:21,934] Trial 12 finished with value: -128.89489818486823 and parameters: {'embedding_dim': 75, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:08:26,906] Trial 13 finished with value: -19.95199803963176 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:08:33,871] Trial 14 finished with value: -38.97167677910623 and parameters: {'embedding_dim': 81, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:08:42,143] Trial 15 finished with value: -18.38785650107637 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:08:47,184] Trial 16 finished with value: -9.770242015607273 and parameters: {'embedding_dim': 86, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:08:54,061] Trial 17 finished with value: -84.48088398373191 and parameters: {'embedding_dim': 76, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:08:58,817] Trial 18 finished with value: -145.56586955765417 and parameters: {'embedding_dim': 99, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:09:04,956] Trial 19 finished with value: -68.37472924681902 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:09:11,669] Trial 20 finished with value: -146.07746495580506 and parameters: {'embedding_dim': 70, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:09:18,643] Trial 21 finished with value: -16.907238518982595 and parameters: {'embedding_dim': 86, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:09:23,792] Trial 22 finished with value: -43.7692261171558 and parameters: {'embedding_dim': 86, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:09:28,924] Trial 23 finished with value: -92.78473730324798 and parameters: {'embedding_dim': 77, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:09:32,318] Trial 24 finished with value: -83.0020004294551 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:09:38,490] Trial 25 finished with value: -6.181407502059026 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:09:44,846] Trial 26 finished with value: -61.023296578806935 and parameters: {'embedding_dim': 68, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:09:49,631] Trial 27 finished with value: -12.130397539307866 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:09:56,047] Trial 28 finished with value: -123.29934144585063 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:09:59,189] Trial 29 finished with value: -94.29045183070981 and parameters: {'embedding_dim': 120, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:10:03,973] Trial 30 finished with value: -14.227097649759324 and parameters: {'embedding_dim': 68, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:10:11,127] Trial 31 finished with value: -81.72818238231812 and parameters: {'embedding_dim': 84, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:10:15,833] Trial 32 finished with value: -74.32343076320043 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:10:20,543] Trial 33 finished with value: -75.45944026027878 and parameters: {'embedding_dim': 74, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:10:23,876] Trial 34 finished with value: -80.0813696314097 and parameters: {'embedding_dim': 81, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:10:29,376] Trial 35 finished with value: -17.269652960090657 and parameters: {'embedding_dim': 69, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:10:34,266] Trial 36 finished with value: -10.825216499975992 and parameters: {'embedding_dim': 96, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:10:39,081] Trial 37 finished with value: -77.59355209428959 and parameters: {'embedding_dim': 109, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:10:43,630] Trial 38 finished with value: -88.69656879374526 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:10:50,228] Trial 39 finished with value: -82.85065064334214 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:10:54,898] Trial 40 finished with value: -56.421324380484236 and parameters: {'embedding_dim': 66, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:10:59,876] Trial 41 finished with value: -85.89815312930149 and parameters: {'embedding_dim': 95, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:11:05,137] Trial 42 finished with value: -122.69060712161212 and parameters: {'embedding_dim': 98, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:11:12,083] Trial 43 finished with value: -19.765880564242497 and parameters: {'embedding_dim': 102, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 8 with value: -4.084881450725948.
+[I 2025-12-18 04:11:17,071] Trial 44 finished with value: -2.2894720102379633 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 44 with value: -2.2894720102379633.
+[I 2025-12-18 04:11:22,254] Trial 45 finished with value: -33.169277797299486 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 44 with value: -2.2894720102379633.
+[I 2025-12-18 04:11:28,969] Trial 46 finished with value: -27.41743721318746 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 44 with value: -2.2894720102379633.
+[I 2025-12-18 04:11:33,730] Trial 47 finished with value: -76.72195878627832 and parameters: {'embedding_dim': 83, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 44 with value: -2.2894720102379633.
+[I 2025-12-18 04:11:39,026] Trial 48 finished with value: -29.429362753570835 and parameters: {'embedding_dim': 66, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 44 with value: -2.2894720102379633.
+[I 2025-12-18 04:11:43,678] Trial 49 finished with value: -10.498069101953572 and parameters: {'embedding_dim': 127, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 44 with value: -2.2894720102379633.
+[I 2025-12-18 04:11:49,021] A new study created in memory with name: no-name-ae6a8579-8954-4166-b8a4-4e0010e37643
+[I 2025-12-18 04:12:04,077] Trial 0 finished with value: -526.6535592236594 and parameters: {'embedding_dim': 503, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -526.6535592236594.
+[I 2025-12-18 04:12:13,458] Trial 1 finished with value: -965.1731009870346 and parameters: {'embedding_dim': 274, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 0 with value: -526.6535592236594.
+[I 2025-12-18 04:12:34,840] Trial 2 finished with value: -175.49993855186008 and parameters: {'embedding_dim': 209, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:12:46,203] Trial 3 finished with value: -1137.5607738998526 and parameters: {'embedding_dim': 449, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:12:51,550] Trial 4 finished with value: -3520.810325337823 and parameters: {'embedding_dim': 474, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:13:10,106] Trial 5 finished with value: -981.0782360569036 and parameters: {'embedding_dim': 350, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:13:21,455] Trial 6 finished with value: -507.78384636253514 and parameters: {'embedding_dim': 194, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:13:30,052] Trial 7 finished with value: -424.9791038019945 and parameters: {'embedding_dim': 375, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:13:48,838] Trial 8 finished with value: -238.67411231366597 and parameters: {'embedding_dim': 181, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:13:58,671] Trial 9 finished with value: -383.98498020877486 and parameters: {'embedding_dim': 364, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:14:17,455] Trial 10 finished with value: -1094.1240162663903 and parameters: {'embedding_dim': 133, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:14:34,490] Trial 11 finished with value: -429.6333786413718 and parameters: {'embedding_dim': 244, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:14:48,526] Trial 12 finished with value: -224.839495710413 and parameters: {'embedding_dim': 139, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:15:07,270] Trial 13 finished with value: -258.13746335307997 and parameters: {'embedding_dim': 130, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:15:18,882] Trial 14 finished with value: -318.65500455561437 and parameters: {'embedding_dim': 222, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:15:32,566] Trial 15 finished with value: -853.4703148826945 and parameters: {'embedding_dim': 273, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:15:51,312] Trial 16 finished with value: -252.60375889445285 and parameters: {'embedding_dim': 180, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:15:59,634] Trial 17 finished with value: -400.32720901739447 and parameters: {'embedding_dim': 293, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:16:22,615] Trial 18 finished with value: -474.0489002077139 and parameters: {'embedding_dim': 156, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:16:34,238] Trial 19 finished with value: -574.8955458597748 and parameters: {'embedding_dim': 225, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:16:49,211] Trial 20 finished with value: -1663.7842852444853 and parameters: {'embedding_dim': 325, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:17:05,737] Trial 21 finished with value: -198.0339289513673 and parameters: {'embedding_dim': 190, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:17:22,228] Trial 22 finished with value: -390.0988348672782 and parameters: {'embedding_dim': 205, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:17:38,774] Trial 23 finished with value: -256.08041395669267 and parameters: {'embedding_dim': 164, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:17:52,532] Trial 24 finished with value: -291.82030607446023 and parameters: {'embedding_dim': 243, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:18:09,076] Trial 25 finished with value: -207.2903329988008 and parameters: {'embedding_dim': 151, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:18:26,118] Trial 26 finished with value: -543.6318604256203 and parameters: {'embedding_dim': 407, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 2 with value: -175.49993855186008.
+[I 2025-12-18 04:18:42,993] Trial 27 finished with value: -153.55486544086202 and parameters: {'embedding_dim': 213, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 27 with value: -153.55486544086202.
+[I 2025-12-18 04:18:56,840] Trial 28 finished with value: -708.7544395042854 and parameters: {'embedding_dim': 255, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 27 with value: -153.55486544086202.
+[I 2025-12-18 04:19:15,838] Trial 29 finished with value: -527.9408479381669 and parameters: {'embedding_dim': 310, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 27 with value: -153.55486544086202.
+[I 2025-12-18 04:19:34,166] A new study created in memory with name: no-name-e9076e98-7d8f-49ae-9a1d-669c8966a072
+[I 2025-12-18 04:19:37,573] Trial 0 finished with value: -63.735866583022606 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 0 with value: -63.735866583022606.
+[I 2025-12-18 04:19:43,064] Trial 1 finished with value: -26.003181394726017 and parameters: {'embedding_dim': 108, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -26.003181394726017.
+[I 2025-12-18 04:19:48,589] Trial 2 finished with value: -43.16172644347499 and parameters: {'embedding_dim': 91, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -26.003181394726017.
+[I 2025-12-18 04:19:54,057] Trial 3 finished with value: -141.2292554604851 and parameters: {'embedding_dim': 67, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -26.003181394726017.
+[I 2025-12-18 04:19:59,148] Trial 4 finished with value: -235.80541032122338 and parameters: {'embedding_dim': 86, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 1 with value: -26.003181394726017.
+[I 2025-12-18 04:20:05,814] Trial 5 finished with value: -212.8895167518603 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 1 with value: -26.003181394726017.
+[I 2025-12-18 04:20:09,234] Trial 6 finished with value: -8.708301472382377 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 6 with value: -8.708301472382377.
+[I 2025-12-18 04:20:12,649] Trial 7 finished with value: -32.90647967889222 and parameters: {'embedding_dim': 87, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 6 with value: -8.708301472382377.
+[I 2025-12-18 04:20:19,334] Trial 8 finished with value: -127.26096620453308 and parameters: {'embedding_dim': 108, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 6 with value: -8.708301472382377.
+[I 2025-12-18 04:20:22,791] Trial 9 finished with value: -83.09950393803575 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 6 with value: -8.708301472382377.
+[I 2025-12-18 04:20:26,289] Trial 10 finished with value: -607.1778241511079 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 6 with value: -8.708301472382377.
+[I 2025-12-18 04:20:31,798] Trial 11 finished with value: -116.08414192372217 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 6 with value: -8.708301472382377.
+[I 2025-12-18 04:20:39,151] Trial 12 finished with value: -87.69479639021313 and parameters: {'embedding_dim': 103, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 6 with value: -8.708301472382377.
+[I 2025-12-18 04:20:42,593] Trial 13 finished with value: -44.04909141575184 and parameters: {'embedding_dim': 117, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 6 with value: -8.708301472382377.
+[I 2025-12-18 04:20:48,056] Trial 14 finished with value: -23.012087059766973 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 6 with value: -8.708301472382377.
+[I 2025-12-18 04:20:51,483] Trial 15 finished with value: -99.40257721079914 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 6 with value: -8.708301472382377.
+[I 2025-12-18 04:20:58,901] Trial 16 finished with value: -203.849287866314 and parameters: {'embedding_dim': 97, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 6 with value: -8.708301472382377.
+[I 2025-12-18 04:21:04,045] Trial 17 finished with value: -123.35776604824194 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 6 with value: -8.708301472382377.
+[I 2025-12-18 04:21:07,661] Trial 18 finished with value: -574.7956969524759 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 6 with value: -8.708301472382377.
+[I 2025-12-18 04:21:12,666] Trial 19 finished with value: -50.31784996871129 and parameters: {'embedding_dim': 119, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 6 with value: -8.708301472382377.
+[I 2025-12-18 04:21:19,432] Trial 20 finished with value: -23.006847307993624 and parameters: {'embedding_dim': 72, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 6 with value: -8.708301472382377.
+[I 2025-12-18 04:21:26,345] Trial 21 finished with value: -36.69258148986405 and parameters: {'embedding_dim': 72, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 6 with value: -8.708301472382377.
+[I 2025-12-18 04:21:33,214] Trial 22 finished with value: -63.26815899346464 and parameters: {'embedding_dim': 69, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 6 with value: -8.708301472382377.
+[I 2025-12-18 04:21:40,226] Trial 23 finished with value: -64.72882164432183 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 6 with value: -8.708301472382377.
+[I 2025-12-18 04:21:45,532] Trial 24 finished with value: -78.9396934481297 and parameters: {'embedding_dim': 80, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 6 with value: -8.708301472382377.
+[I 2025-12-18 04:21:50,974] Trial 25 finished with value: -14.482616565215778 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 6 with value: -8.708301472382377.
+[I 2025-12-18 04:21:56,033] Trial 26 finished with value: -101.66623027558283 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 6 with value: -8.708301472382377.
+[I 2025-12-18 04:21:59,540] Trial 27 finished with value: -7.331627402030013 and parameters: {'embedding_dim': 72, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 27 with value: -7.331627402030013.
+[I 2025-12-18 04:22:02,879] Trial 28 finished with value: -205.6472284542831 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 27 with value: -7.331627402030013.
+[I 2025-12-18 04:22:06,461] Trial 29 finished with value: -39.21297782664432 and parameters: {'embedding_dim': 65, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 27 with value: -7.331627402030013.
+[I 2025-12-18 04:22:09,876] Trial 30 finished with value: -79.5163926534601 and parameters: {'embedding_dim': 80, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 27 with value: -7.331627402030013.
+[I 2025-12-18 04:22:13,310] Trial 31 finished with value: -69.61364279685 and parameters: {'embedding_dim': 69, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 27 with value: -7.331627402030013.
+[I 2025-12-18 04:22:16,861] Trial 32 finished with value: -299.8182590096131 and parameters: {'embedding_dim': 72, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 27 with value: -7.331627402030013.
+[I 2025-12-18 04:22:22,011] Trial 33 finished with value: -53.48982817424692 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 27 with value: -7.331627402030013.
+[I 2025-12-18 04:22:25,410] Trial 34 finished with value: -188.5133722618799 and parameters: {'embedding_dim': 79, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 27 with value: -7.331627402030013.
+[I 2025-12-18 04:22:30,988] Trial 35 finished with value: -12.359760429978131 and parameters: {'embedding_dim': 65, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 27 with value: -7.331627402030013.
+[I 2025-12-18 04:22:36,484] Trial 36 finished with value: -181.8738648476388 and parameters: {'embedding_dim': 66, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 27 with value: -7.331627402030013.
+[I 2025-12-18 04:22:41,945] Trial 37 finished with value: -311.45704109834145 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 27 with value: -7.331627402030013.
+[I 2025-12-18 04:22:47,584] Trial 38 finished with value: -5.72875940004749 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 38 with value: -5.72875940004749.
+[I 2025-12-18 04:22:53,046] Trial 39 finished with value: -28.800448607794742 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 38 with value: -5.72875940004749.
+[I 2025-12-18 04:22:56,678] Trial 40 finished with value: -113.12842462418543 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 38 with value: -5.72875940004749.
+[I 2025-12-18 04:23:02,154] Trial 41 finished with value: -73.26326959239282 and parameters: {'embedding_dim': 88, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 38 with value: -5.72875940004749.
+[I 2025-12-18 04:23:07,911] Trial 42 finished with value: -24.35401970375804 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 38 with value: -5.72875940004749.
+[I 2025-12-18 04:23:13,367] Trial 43 finished with value: -24.64392419974173 and parameters: {'embedding_dim': 69, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 38 with value: -5.72875940004749.
+[I 2025-12-18 04:23:18,871] Trial 44 finished with value: -28.140811034117366 and parameters: {'embedding_dim': 94, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 38 with value: -5.72875940004749.
+[I 2025-12-18 04:23:23,866] Trial 45 finished with value: -56.09684366334129 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 38 with value: -5.72875940004749.
+[I 2025-12-18 04:23:27,429] Trial 46 finished with value: -5.199064425219974 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 46 with value: -5.199064425219974.
+[I 2025-12-18 04:23:31,196] Trial 47 finished with value: -15.109828303025475 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 46 with value: -5.199064425219974.
+[I 2025-12-18 04:23:34,891] Trial 48 finished with value: -251.77025928651224 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 46 with value: -5.199064425219974.
+[I 2025-12-18 04:23:38,213] Trial 49 finished with value: -14.055296615679172 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 46 with value: -5.199064425219974.
+[I 2025-12-18 04:23:42,271] A new study created in memory with name: no-name-a063daac-116a-4ae6-a9e3-5e580788dc65
+[I 2025-12-18 04:24:28,047] Trial 0 finished with value: -139.47905108848232 and parameters: {'embedding_dim': 356, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -139.47905108848232.
+[I 2025-12-18 04:25:36,844] Trial 1 finished with value: -127.47704955799753 and parameters: {'embedding_dim': 505, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:26:46,954] Trial 2 finished with value: -1135.172308932939 and parameters: {'embedding_dim': 332, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:27:03,883] Trial 3 finished with value: -518.6148170747557 and parameters: {'embedding_dim': 437, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:27:44,483] Trial 4 finished with value: -650.4784758041819 and parameters: {'embedding_dim': 316, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:28:03,978] Trial 5 finished with value: -807.4972451644614 and parameters: {'embedding_dim': 250, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:28:21,664] Trial 6 finished with value: -2212.8825763468344 and parameters: {'embedding_dim': 266, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:28:56,701] Trial 7 finished with value: -684.039575998659 and parameters: {'embedding_dim': 333, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:29:31,069] Trial 8 finished with value: -763.8331756845621 and parameters: {'embedding_dim': 151, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:30:17,646] Trial 9 finished with value: -339.2082636005923 and parameters: {'embedding_dim': 375, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:30:32,307] Trial 10 finished with value: -3138.65515602725 and parameters: {'embedding_dim': 504, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:31:18,985] Trial 11 finished with value: -258.7473008442672 and parameters: {'embedding_dim': 470, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:32:17,528] Trial 12 finished with value: -796.0798001243425 and parameters: {'embedding_dim': 424, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:32:51,335] Trial 13 finished with value: -2286.089416128079 and parameters: {'embedding_dim': 159, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:33:37,146] Trial 14 finished with value: -2954.146933621371 and parameters: {'embedding_dim': 395, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:34:12,652] Trial 15 finished with value: -1645.437381402957 and parameters: {'embedding_dim': 504, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:34:36,311] Trial 16 finished with value: -4944.072922495291 and parameters: {'embedding_dim': 218, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:35:10,360] Trial 17 finished with value: -2147.3181278240536 and parameters: {'embedding_dim': 371, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:35:24,369] Trial 18 finished with value: -466.23048801487266 and parameters: {'embedding_dim': 459, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:35:59,885] Trial 19 finished with value: -896.8925630373876 and parameters: {'embedding_dim': 279, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:37:08,119] Trial 20 finished with value: -198.7821901456314 and parameters: {'embedding_dim': 197, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:38:17,527] Trial 21 finished with value: -1019.6839434625649 and parameters: {'embedding_dim': 209, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:39:26,059] Trial 22 finished with value: -301.9860193820961 and parameters: {'embedding_dim': 189, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:40:23,532] Trial 23 finished with value: -790.483874232549 and parameters: {'embedding_dim': 236, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:41:32,564] Trial 24 finished with value: -195.3939212055289 and parameters: {'embedding_dim': 131, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:42:17,971] Trial 25 finished with value: -3745.1612358490884 and parameters: {'embedding_dim': 282, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:43:14,623] Trial 26 finished with value: -426.8382004283499 and parameters: {'embedding_dim': 310, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:44:24,889] Trial 27 finished with value: -558.2863234157112 and parameters: {'embedding_dim': 408, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:44:52,867] Trial 28 finished with value: -2627.615690221205 and parameters: {'embedding_dim': 133, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:45:13,722] Trial 29 finished with value: -409.2675055329187 and parameters: {'embedding_dim': 348, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 1 with value: -127.47704955799753.
+[I 2025-12-18 04:46:24,130] A new study created in memory with name: no-name-d88ab3b5-5cbf-4be7-a4d3-9421abdc05a2
+[I 2025-12-18 04:46:30,585] Trial 0 finished with value: -10.561478766081269 and parameters: {'embedding_dim': 94, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:46:35,490] Trial 1 finished with value: -112.01089039613156 and parameters: {'embedding_dim': 76, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:46:42,150] Trial 2 finished with value: -16.53928250015679 and parameters: {'embedding_dim': 67, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:46:47,493] Trial 3 finished with value: -28.066141224766184 and parameters: {'embedding_dim': 88, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:46:50,683] Trial 4 finished with value: -221.1205469186096 and parameters: {'embedding_dim': 99, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:46:57,442] Trial 5 finished with value: -76.33927504746973 and parameters: {'embedding_dim': 116, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:47:02,312] Trial 6 finished with value: -163.38553874461408 and parameters: {'embedding_dim': 65, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:47:07,655] Trial 7 finished with value: -186.86411643164735 and parameters: {'embedding_dim': 66, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:47:14,373] Trial 8 finished with value: -127.8101924755967 and parameters: {'embedding_dim': 108, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:47:17,687] Trial 9 finished with value: -21.526863178218036 and parameters: {'embedding_dim': 103, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:47:24,248] Trial 10 finished with value: -64.90070262184148 and parameters: {'embedding_dim': 126, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:47:30,649] Trial 11 finished with value: -76.21976135184245 and parameters: {'embedding_dim': 83, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:47:37,446] Trial 12 finished with value: -57.69713796574893 and parameters: {'embedding_dim': 88, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:47:43,997] Trial 13 finished with value: -18.261261994355344 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:47:51,417] Trial 14 finished with value: -93.55233500605203 and parameters: {'embedding_dim': 114, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:47:56,619] Trial 15 finished with value: -20.77022004213259 and parameters: {'embedding_dim': 94, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:48:03,212] Trial 16 finished with value: -75.045760002752 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:48:06,479] Trial 17 finished with value: -48.69460467261395 and parameters: {'embedding_dim': 127, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:48:11,617] Trial 18 finished with value: -196.7123138089014 and parameters: {'embedding_dim': 70, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:48:19,003] Trial 19 finished with value: -78.32724225367117 and parameters: {'embedding_dim': 83, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:48:24,000] Trial 20 finished with value: -41.45745039091709 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:48:30,454] Trial 21 finished with value: -46.169565643409925 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:48:36,987] Trial 22 finished with value: -41.42248189760822 and parameters: {'embedding_dim': 81, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:48:43,413] Trial 23 finished with value: -12.826582351050972 and parameters: {'embedding_dim': 70, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:48:49,890] Trial 24 finished with value: -41.90990281143064 and parameters: {'embedding_dim': 70, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:48:56,388] Trial 25 finished with value: -43.980892407831774 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:49:02,868] Trial 26 finished with value: -183.1248933110248 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:49:07,660] Trial 27 finished with value: -82.9452207351605 and parameters: {'embedding_dim': 69, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:49:14,871] Trial 28 finished with value: -64.10170443803597 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:49:19,920] Trial 29 finished with value: -31.36687221581477 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:49:26,670] Trial 30 finished with value: -65.30608396162441 and parameters: {'embedding_dim': 71, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:49:33,125] Trial 31 finished with value: -122.56608075567844 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:49:39,597] Trial 32 finished with value: -38.322052718405416 and parameters: {'embedding_dim': 88, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:49:46,068] Trial 33 finished with value: -72.55703887169408 and parameters: {'embedding_dim': 78, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:49:52,520] Trial 34 finished with value: -42.39472502387662 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:49:59,006] Trial 35 finished with value: -67.2387988077623 and parameters: {'embedding_dim': 71, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:50:02,431] Trial 36 finished with value: -54.774286845030716 and parameters: {'embedding_dim': 67, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:50:08,939] Trial 37 finished with value: -69.49549630036582 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:50:13,922] Trial 38 finished with value: -36.88276749068735 and parameters: {'embedding_dim': 109, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:50:20,751] Trial 39 finished with value: -186.91563760291524 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:50:25,823] Trial 40 finished with value: -118.89206592540921 and parameters: {'embedding_dim': 79, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:50:30,742] Trial 41 finished with value: -113.94116147602104 and parameters: {'embedding_dim': 94, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:50:35,777] Trial 42 finished with value: -28.95418227818631 and parameters: {'embedding_dim': 100, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:50:40,878] Trial 43 finished with value: -75.34686016490875 and parameters: {'embedding_dim': 91, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:50:44,233] Trial 44 finished with value: -40.14345444011659 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:50:51,035] Trial 45 finished with value: -69.99860411642858 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:50:56,382] Trial 46 finished with value: -264.33991269912997 and parameters: {'embedding_dim': 67, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:51:02,892] Trial 47 finished with value: -60.15997424600581 and parameters: {'embedding_dim': 118, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:51:09,596] Trial 48 finished with value: -74.3982330838299 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:51:14,480] Trial 49 finished with value: -207.29047096501665 and parameters: {'embedding_dim': 73, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -10.561478766081269.
+[I 2025-12-18 04:51:21,528] A new study created in memory with name: no-name-1330e8b1-65b2-44d3-9be9-97347c3d54c0
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_20000_2_seoul_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_20000_2_seoul_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan20000_2_seoul.csv: Class 0=17506 | Class 1=17683
+Saved ../../data/data_oversampled/ctgan20000/ctgan20000_2_seoul.csv: Class 0=17535 | Class 1=19375 | Class 2=15823
+Processing ../../data/data_for_modeling/busan_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/busan_train.csv: Optimizing CTGAN for class 1...
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_20000_2_busan_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_20000_2_busan_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan20000_2_busan.csv: Class 0=19773 | Class 1=16959
+Saved ../../data/data_oversampled/ctgan20000/ctgan20000_2_busan.csv: Class 0=19848 | Class 1=17971 | Class 2=16457
+Processing ../../data/data_for_modeling/daegu_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/daegu_train.csv: Optimizing CTGAN for class 1...
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_20000_2_daegu_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_20000_2_daegu_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan20000_2_daegu.csv: Class 0=19794 | Class 1=17360
+Saved ../../data/data_oversampled/ctgan20000/ctgan20000_2_daegu.csv: Class 0=19823 | Class 1=18072 | Class 2=16803
+Processing ../../data/data_for_modeling/daejeon_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/daejeon_train.csv: Optimizing CTGAN for class 1...
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_20000_2_daejeon_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_20000_2_daejeon_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan20000_2_daejeon.csv: Class 0=18108 | Class 1=15759
+Saved ../../data/data_oversampled/ctgan20000/ctgan20000_2_daejeon.csv: Class 0=18224 | Class 1=17470 | Class 2=15717
+Processing ../../data/data_for_modeling/gwangju_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/gwangju_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-18 04:51:59,057] Trial 0 finished with value: -1392.544708797632 and parameters: {'embedding_dim': 382, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 0 with value: -1392.544708797632.
+[I 2025-12-18 04:52:39,790] Trial 1 finished with value: -1022.9484868132945 and parameters: {'embedding_dim': 139, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 1 with value: -1022.9484868132945.
+[I 2025-12-18 04:53:15,312] Trial 2 finished with value: -798.0110561883089 and parameters: {'embedding_dim': 479, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 2 with value: -798.0110561883089.
+[I 2025-12-18 04:53:23,274] Trial 3 finished with value: -2081.8561095879604 and parameters: {'embedding_dim': 422, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 2 with value: -798.0110561883089.
+[I 2025-12-18 04:53:37,461] Trial 4 finished with value: -977.5038095380651 and parameters: {'embedding_dim': 264, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 2 with value: -798.0110561883089.
+[I 2025-12-18 04:54:11,919] Trial 5 finished with value: -1000.9518859693735 and parameters: {'embedding_dim': 161, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -798.0110561883089.
+[I 2025-12-18 04:54:46,289] Trial 6 finished with value: -1171.654622180594 and parameters: {'embedding_dim': 484, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 2 with value: -798.0110561883089.
+[I 2025-12-18 04:55:09,119] Trial 7 finished with value: -102.05161926979335 and parameters: {'embedding_dim': 372, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -102.05161926979335.
+[I 2025-12-18 04:55:26,158] Trial 8 finished with value: -530.7675055770017 and parameters: {'embedding_dim': 367, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 7 with value: -102.05161926979335.
+[I 2025-12-18 04:55:47,557] Trial 9 finished with value: -393.2799133535036 and parameters: {'embedding_dim': 250, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 7 with value: -102.05161926979335.
+[I 2025-12-18 04:56:22,195] Trial 10 finished with value: -537.2270484956714 and parameters: {'embedding_dim': 301, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 7 with value: -102.05161926979335.
+[I 2025-12-18 04:56:57,130] Trial 11 finished with value: -109.60845722927496 and parameters: {'embedding_dim': 235, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 7 with value: -102.05161926979335.
+[I 2025-12-18 04:57:20,622] Trial 12 finished with value: -590.5967115531727 and parameters: {'embedding_dim': 206, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -102.05161926979335.
+[I 2025-12-18 04:57:54,898] Trial 13 finished with value: -200.30465331906683 and parameters: {'embedding_dim': 327, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 7 with value: -102.05161926979335.
+[I 2025-12-18 04:58:41,507] Trial 14 finished with value: -96.09960991329243 and parameters: {'embedding_dim': 220, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -96.09960991329243.
+[I 2025-12-18 04:59:27,748] Trial 15 finished with value: -164.2848152599352 and parameters: {'embedding_dim': 306, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -96.09960991329243.
+[I 2025-12-18 05:00:13,577] Trial 16 finished with value: -226.10862365427855 and parameters: {'embedding_dim': 185, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -96.09960991329243.
+[I 2025-12-18 05:01:23,109] Trial 17 finished with value: -168.78750246560915 and parameters: {'embedding_dim': 420, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 14 with value: -96.09960991329243.
+[I 2025-12-18 05:01:38,095] Trial 18 finished with value: -599.9181571864398 and parameters: {'embedding_dim': 334, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 14 with value: -96.09960991329243.
+[I 2025-12-18 05:02:23,767] Trial 19 finished with value: -45.1740703562058 and parameters: {'embedding_dim': 280, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 19 with value: -45.1740703562058.
+[I 2025-12-18 05:03:08,924] Trial 20 finished with value: -1030.475577179196 and parameters: {'embedding_dim': 216, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 19 with value: -45.1740703562058.
+[I 2025-12-18 05:03:54,982] Trial 21 finished with value: -474.3942416148369 and parameters: {'embedding_dim': 276, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 19 with value: -45.1740703562058.
+[I 2025-12-18 05:04:23,553] Trial 22 finished with value: -15.474083947469088 and parameters: {'embedding_dim': 374, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 22 with value: -15.474083947469088.
+[I 2025-12-18 05:05:12,595] Trial 23 finished with value: -146.115377173385 and parameters: {'embedding_dim': 291, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 22 with value: -15.474083947469088.
+[I 2025-12-18 05:06:11,709] Trial 24 finished with value: -91.13605055571794 and parameters: {'embedding_dim': 344, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 22 with value: -15.474083947469088.
+[I 2025-12-18 05:06:32,897] Trial 25 finished with value: -517.2486162536821 and parameters: {'embedding_dim': 418, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 22 with value: -15.474083947469088.
+[I 2025-12-18 05:07:31,521] Trial 26 finished with value: -154.68732516393743 and parameters: {'embedding_dim': 348, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 22 with value: -15.474083947469088.
+[I 2025-12-18 05:08:42,547] Trial 27 finished with value: -833.2360159849594 and parameters: {'embedding_dim': 401, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 22 with value: -15.474083947469088.
+[I 2025-12-18 05:09:41,994] Trial 28 finished with value: -43.78244619037278 and parameters: {'embedding_dim': 461, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 22 with value: -15.474083947469088.
+[I 2025-12-18 05:10:00,736] Trial 29 finished with value: -570.2312341833735 and parameters: {'embedding_dim': 456, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 22 with value: -15.474083947469088.
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_20000_2_gwangju_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_20000_2_gwangju_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan20000_2_gwangju.csv: Class 0=16318 | Class 1=17653
+Saved ../../data/data_oversampled/ctgan20000/ctgan20000_2_gwangju.csv: Class 0=16397 | Class 1=19358 | Class 2=15760
+
+Running ctgan_sample_20000_3.py...
+[I 2025-12-18 05:10:29,518] A new study created in memory with name: no-name-f549697f-bcf8-4881-9399-431f9db864a8
+[I 2025-12-18 05:10:34,471] Trial 0 finished with value: -21.007255778488698 and parameters: {'embedding_dim': 121, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -21.007255778488698.
+[I 2025-12-18 05:10:44,498] Trial 1 finished with value: -12.629549372716752 and parameters: {'embedding_dim': 116, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 1 with value: -12.629549372716752.
+[I 2025-12-18 05:10:58,999] Trial 2 finished with value: -432.4144432646718 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 1 with value: -12.629549372716752.
+[I 2025-12-18 05:11:23,994] Trial 3 finished with value: -114.68729513493189 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 1 with value: -12.629549372716752.
+[I 2025-12-18 05:11:33,992] Trial 4 finished with value: -1.0850892337793485 and parameters: {'embedding_dim': 115, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -1.0850892337793485.
+[I 2025-12-18 05:11:37,874] Trial 5 finished with value: -39.92662603758006 and parameters: {'embedding_dim': 118, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 4 with value: -1.0850892337793485.
+[I 2025-12-18 05:11:53,106] Trial 6 finished with value: -8.963274156139224 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 4 with value: -1.0850892337793485.
+[I 2025-12-18 05:12:00,745] Trial 7 finished with value: -4.199804119474114 and parameters: {'embedding_dim': 71, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -1.0850892337793485.
+[I 2025-12-18 05:12:12,680] Trial 8 finished with value: -266.649323359913 and parameters: {'embedding_dim': 70, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 4 with value: -1.0850892337793485.
+[I 2025-12-18 05:12:26,151] Trial 9 finished with value: -6.08899406362311 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 4 with value: -1.0850892337793485.
+[I 2025-12-18 05:12:36,216] Trial 10 finished with value: -113.29093102511374 and parameters: {'embedding_dim': 105, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 4 with value: -1.0850892337793485.
+[I 2025-12-18 05:12:41,997] Trial 11 finished with value: -14.98245225141249 and parameters: {'embedding_dim': 66, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 4 with value: -1.0850892337793485.
+[I 2025-12-18 05:12:51,907] Trial 12 finished with value: -0.4610671866703371 and parameters: {'embedding_dim': 104, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:13:01,948] Trial 13 finished with value: -106.49028031450938 and parameters: {'embedding_dim': 105, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:13:07,719] Trial 14 finished with value: -35.296066045634866 and parameters: {'embedding_dim': 128, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:13:21,180] Trial 15 finished with value: -6.210984846670829 and parameters: {'embedding_dim': 104, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:13:27,255] Trial 16 finished with value: -16.5764068311653 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:13:42,814] Trial 17 finished with value: -16.41977736060856 and parameters: {'embedding_dim': 110, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:13:48,626] Trial 18 finished with value: -6.064672384936593 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:14:08,453] Trial 19 finished with value: -63.38380169659574 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:14:15,994] Trial 20 finished with value: -21.70280699968727 and parameters: {'embedding_dim': 99, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:14:23,656] Trial 21 finished with value: -50.087512563391385 and parameters: {'embedding_dim': 74, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:14:32,992] Trial 22 finished with value: -8.670793278351384 and parameters: {'embedding_dim': 112, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:14:40,641] Trial 23 finished with value: -24.695717453866013 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:14:48,279] Trial 24 finished with value: -16.061303433658576 and parameters: {'embedding_dim': 99, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:14:58,314] Trial 25 finished with value: -11.7236665050597 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:15:05,975] Trial 26 finished with value: -13.849590099250264 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:15:13,474] Trial 27 finished with value: -87.00685396074435 and parameters: {'embedding_dim': 65, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:15:38,536] Trial 28 finished with value: -68.18368843924092 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:15:45,102] Trial 29 finished with value: -153.8708206302535 and parameters: {'embedding_dim': 125, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:15:50,899] Trial 30 finished with value: -12.731914065236378 and parameters: {'embedding_dim': 114, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:15:56,665] Trial 31 finished with value: -25.582520119755788 and parameters: {'embedding_dim': 124, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:16:02,427] Trial 32 finished with value: -16.888273814049622 and parameters: {'embedding_dim': 108, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:16:08,233] Trial 33 finished with value: -25.182693786320222 and parameters: {'embedding_dim': 121, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:16:12,136] Trial 34 finished with value: -9.766846989449423 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:16:17,910] Trial 35 finished with value: -82.91655647122107 and parameters: {'embedding_dim': 116, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:16:38,082] Trial 36 finished with value: -2.3272723261453443 and parameters: {'embedding_dim': 122, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:16:50,088] Trial 37 finished with value: -59.665116081650424 and parameters: {'embedding_dim': 117, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:17:16,563] Trial 38 finished with value: -39.700641884514155 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:17:43,563] Trial 39 finished with value: -87.82197484836337 and parameters: {'embedding_dim': 121, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:18:02,159] Trial 40 finished with value: -74.61014354308156 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:18:20,678] Trial 41 finished with value: -13.893591126033357 and parameters: {'embedding_dim': 123, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:18:30,713] Trial 42 finished with value: -5.802071960621702 and parameters: {'embedding_dim': 120, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:18:40,778] Trial 43 finished with value: -33.21725377663893 and parameters: {'embedding_dim': 115, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:18:53,164] Trial 44 finished with value: -15.290827584962713 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:19:03,204] Trial 45 finished with value: -87.40622535761462 and parameters: {'embedding_dim': 108, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:19:09,793] Trial 46 finished with value: -46.724630189520944 and parameters: {'embedding_dim': 71, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:19:19,833] Trial 47 finished with value: -41.19090898431512 and parameters: {'embedding_dim': 113, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:19:29,883] Trial 48 finished with value: -14.59387994692349 and parameters: {'embedding_dim': 107, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:19:43,266] Trial 49 finished with value: -6.175691003736937 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 12 with value: -0.4610671866703371.
+[I 2025-12-18 05:19:51,159] A new study created in memory with name: no-name-34a52129-afa0-4a70-b2a0-42bf6a7049f9
+Using device: cuda
+Processing ../../data/data_for_modeling/incheon_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/incheon_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-18 05:20:29,341] Trial 0 finished with value: -1002.2946228263336 and parameters: {'embedding_dim': 374, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 0 with value: -1002.2946228263336.
+[I 2025-12-18 05:21:08,550] Trial 1 finished with value: -343.1124263790541 and parameters: {'embedding_dim': 229, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 1 with value: -343.1124263790541.
+[I 2025-12-18 05:22:15,897] Trial 2 finished with value: -559.3710862820304 and parameters: {'embedding_dim': 421, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 1 with value: -343.1124263790541.
+[I 2025-12-18 05:23:54,343] Trial 3 finished with value: -584.4828729343699 and parameters: {'embedding_dim': 399, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 1 with value: -343.1124263790541.
+[I 2025-12-18 05:24:33,494] Trial 4 finished with value: -737.1863164431629 and parameters: {'embedding_dim': 475, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 1 with value: -343.1124263790541.
+[I 2025-12-18 05:26:30,633] Trial 5 finished with value: -200.6387596170166 and parameters: {'embedding_dim': 432, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 5 with value: -200.6387596170166.
+[I 2025-12-18 05:27:40,663] Trial 6 finished with value: -42.396571694191266 and parameters: {'embedding_dim': 474, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 6 with value: -42.396571694191266.
+[I 2025-12-18 05:28:58,109] Trial 7 finished with value: -518.3226322659593 and parameters: {'embedding_dim': 169, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 6 with value: -42.396571694191266.
+[I 2025-12-18 05:29:36,123] Trial 8 finished with value: -178.20692624313693 and parameters: {'embedding_dim': 219, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 6 with value: -42.396571694191266.
+[I 2025-12-18 05:30:10,970] Trial 9 finished with value: -291.6654918879053 and parameters: {'embedding_dim': 360, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 6 with value: -42.396571694191266.
+[I 2025-12-18 05:31:07,215] Trial 10 finished with value: -146.64581044693236 and parameters: {'embedding_dim': 301, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 6 with value: -42.396571694191266.
+[I 2025-12-18 05:32:04,043] Trial 11 finished with value: -382.8293834502654 and parameters: {'embedding_dim': 287, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 6 with value: -42.396571694191266.
+[I 2025-12-18 05:33:01,431] Trial 12 finished with value: -39.824200018529275 and parameters: {'embedding_dim': 509, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 12 with value: -39.824200018529275.
+[I 2025-12-18 05:33:46,692] Trial 13 finished with value: -182.27247255922111 and parameters: {'embedding_dim': 498, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 12 with value: -39.824200018529275.
+[I 2025-12-18 05:34:43,346] Trial 14 finished with value: -1000.2245580757562 and parameters: {'embedding_dim': 497, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 12 with value: -39.824200018529275.
+[I 2025-12-18 05:35:40,024] Trial 15 finished with value: -92.94398558722186 and parameters: {'embedding_dim': 447, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 12 with value: -39.824200018529275.
+[I 2025-12-18 05:36:17,154] Trial 16 finished with value: -928.4562872657567 and parameters: {'embedding_dim': 511, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 12 with value: -39.824200018529275.
+[I 2025-12-18 05:37:03,402] Trial 17 finished with value: -7.03819432108719 and parameters: {'embedding_dim': 458, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 17 with value: -7.03819432108719.
+[I 2025-12-18 05:37:37,101] Trial 18 finished with value: -219.67558098097157 and parameters: {'embedding_dim': 375, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 17 with value: -7.03819432108719.
+[I 2025-12-18 05:38:02,915] Trial 19 finished with value: -783.2313658528614 and parameters: {'embedding_dim': 350, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 17 with value: -7.03819432108719.
+[I 2025-12-18 05:38:25,725] Trial 20 finished with value: -4204.298020120994 and parameters: {'embedding_dim': 459, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 17 with value: -7.03819432108719.
+[I 2025-12-18 05:39:12,289] Trial 21 finished with value: -799.504899961848 and parameters: {'embedding_dim': 456, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 17 with value: -7.03819432108719.
+[I 2025-12-18 05:40:09,914] Trial 22 finished with value: -251.60935584302047 and parameters: {'embedding_dim': 412, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 17 with value: -7.03819432108719.
+[I 2025-12-18 05:40:56,519] Trial 23 finished with value: -396.5962779943544 and parameters: {'embedding_dim': 477, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 17 with value: -7.03819432108719.
+[I 2025-12-18 05:41:56,521] Trial 24 finished with value: -83.3031762614885 and parameters: {'embedding_dim': 503, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 17 with value: -7.03819432108719.
+[I 2025-12-18 05:43:05,250] Trial 25 finished with value: -315.37996503185036 and parameters: {'embedding_dim': 404, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 17 with value: -7.03819432108719.
+[I 2025-12-18 05:43:40,927] Trial 26 finished with value: -136.65991755164507 and parameters: {'embedding_dim': 336, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 17 with value: -7.03819432108719.
+[I 2025-12-18 05:44:30,248] Trial 27 finished with value: -37.84243355099008 and parameters: {'embedding_dim': 471, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 17 with value: -7.03819432108719.
+[I 2025-12-18 05:44:55,498] Trial 28 finished with value: -470.8692160322643 and parameters: {'embedding_dim': 438, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 17 with value: -7.03819432108719.
+[I 2025-12-18 05:45:54,469] Trial 29 finished with value: -1054.5426618132929 and parameters: {'embedding_dim': 379, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 17 with value: -7.03819432108719.
+[I 2025-12-18 05:46:43,452] A new study created in memory with name: no-name-273586d6-6303-407b-a5d5-72bb5aefeb75
+[I 2025-12-18 05:46:50,432] Trial 0 finished with value: -172.28164997104778 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -172.28164997104778.
+[I 2025-12-18 05:46:53,484] Trial 1 finished with value: -493.02228401690405 and parameters: {'embedding_dim': 95, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -172.28164997104778.
+[I 2025-12-18 05:46:59,773] Trial 2 finished with value: -185.74493561674385 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -172.28164997104778.
+[I 2025-12-18 05:47:03,070] Trial 3 finished with value: -416.17810696183926 and parameters: {'embedding_dim': 101, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -172.28164997104778.
+[I 2025-12-18 05:47:07,790] Trial 4 finished with value: -412.8170508381159 and parameters: {'embedding_dim': 120, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -172.28164997104778.
+[I 2025-12-18 05:47:14,783] Trial 5 finished with value: -70.22141667505406 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 5 with value: -70.22141667505406.
+[I 2025-12-18 05:47:19,473] Trial 6 finished with value: -702.8040602387066 and parameters: {'embedding_dim': 121, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 5 with value: -70.22141667505406.
+[I 2025-12-18 05:47:24,138] Trial 7 finished with value: -481.19744807015115 and parameters: {'embedding_dim': 83, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 5 with value: -70.22141667505406.
+[I 2025-12-18 05:47:27,446] Trial 8 finished with value: -146.91504342400117 and parameters: {'embedding_dim': 93, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 5 with value: -70.22141667505406.
+[I 2025-12-18 05:47:34,454] Trial 9 finished with value: -157.04487160867953 and parameters: {'embedding_dim': 98, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 5 with value: -70.22141667505406.
+[I 2025-12-18 05:47:40,991] Trial 10 finished with value: -196.4864153280943 and parameters: {'embedding_dim': 65, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 5 with value: -70.22141667505406.
+[I 2025-12-18 05:47:44,281] Trial 11 finished with value: -119.09800608348334 and parameters: {'embedding_dim': 70, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 5 with value: -70.22141667505406.
+[I 2025-12-18 05:47:47,597] Trial 12 finished with value: -266.4433949660183 and parameters: {'embedding_dim': 66, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 5 with value: -70.22141667505406.
+[I 2025-12-18 05:47:53,989] Trial 13 finished with value: -214.2884613406991 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 5 with value: -70.22141667505406.
+[I 2025-12-18 05:47:59,160] Trial 14 finished with value: -32.684727131589156 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:48:04,335] Trial 15 finished with value: -304.65034817283043 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:48:11,950] Trial 16 finished with value: -171.29490891543495 and parameters: {'embedding_dim': 108, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:48:18,051] Trial 17 finished with value: -82.60490257633542 and parameters: {'embedding_dim': 73, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:48:25,112] Trial 18 finished with value: -372.4365381917648 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:48:30,314] Trial 19 finished with value: -43.61973085460277 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:48:36,792] Trial 20 finished with value: -499.0991665174467 and parameters: {'embedding_dim': 85, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:48:41,982] Trial 21 finished with value: -321.1741204759533 and parameters: {'embedding_dim': 71, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:48:47,170] Trial 22 finished with value: -393.17288982446274 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:48:52,361] Trial 23 finished with value: -205.2213952537321 and parameters: {'embedding_dim': 75, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:49:01,453] Trial 24 finished with value: -107.71916494394713 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:49:06,632] Trial 25 finished with value: -129.78234276021254 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:49:13,416] Trial 26 finished with value: -180.3662547340677 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:49:20,422] Trial 27 finished with value: -254.00980521560672 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:49:25,272] Trial 28 finished with value: -186.07087009630231 and parameters: {'embedding_dim': 88, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:49:33,828] Trial 29 finished with value: -98.53643807316038 and parameters: {'embedding_dim': 69, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:49:40,923] Trial 30 finished with value: -97.28256707024968 and parameters: {'embedding_dim': 74, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:49:45,802] Trial 31 finished with value: -39.14361560512981 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:49:50,671] Trial 32 finished with value: -307.7104338960919 and parameters: {'embedding_dim': 68, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:49:55,533] Trial 33 finished with value: -34.08097183116256 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:50:00,407] Trial 34 finished with value: -295.9861190810175 and parameters: {'embedding_dim': 81, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:50:03,548] Trial 35 finished with value: -181.97926533276436 and parameters: {'embedding_dim': 88, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:50:08,417] Trial 36 finished with value: -231.41419337247027 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:50:13,253] Trial 37 finished with value: -470.4064255333032 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:50:17,933] Trial 38 finished with value: -84.57560333330647 and parameters: {'embedding_dim': 73, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:50:21,090] Trial 39 finished with value: -406.3062041511953 and parameters: {'embedding_dim': 81, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:50:25,773] Trial 40 finished with value: -79.67079680656849 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:50:32,212] Trial 41 finished with value: -132.7892564250319 and parameters: {'embedding_dim': 67, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:50:36,888] Trial 42 finished with value: -293.19307779620823 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:50:42,040] Trial 43 finished with value: -350.7647859656338 and parameters: {'embedding_dim': 67, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 14 with value: -32.684727131589156.
+[I 2025-12-18 05:50:46,917] Trial 44 finished with value: -30.555982679907693 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 44 with value: -30.555982679907693.
+[I 2025-12-18 05:50:51,784] Trial 45 finished with value: -77.77020592118211 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 44 with value: -30.555982679907693.
+[I 2025-12-18 05:50:56,663] Trial 46 finished with value: -32.35094854983115 and parameters: {'embedding_dim': 85, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 44 with value: -30.555982679907693.
+[I 2025-12-18 05:50:59,848] Trial 47 finished with value: -213.26506229309342 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 44 with value: -30.555982679907693.
+[I 2025-12-18 05:51:05,041] Trial 48 finished with value: -280.5834695070497 and parameters: {'embedding_dim': 96, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 44 with value: -30.555982679907693.
+[I 2025-12-18 05:51:09,924] Trial 49 finished with value: -63.9408041739183 and parameters: {'embedding_dim': 85, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 44 with value: -30.555982679907693.
+[I 2025-12-18 05:51:15,148] A new study created in memory with name: no-name-cef59868-c2ff-412c-a4ae-379baec550e6
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_20000_3_incheon_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_20000_3_incheon_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan20000_3_incheon.csv: Class 0=18161 | Class 1=16113
+Saved ../../data/data_oversampled/ctgan20000/ctgan20000_3_incheon.csv: Class 0=18468 | Class 1=18755 | Class 2=14595
+Processing ../../data/data_for_modeling/seoul_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/seoul_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-18 05:51:34,306] Trial 0 finished with value: -1460.1246979043167 and parameters: {'embedding_dim': 178, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 0 with value: -1460.1246979043167.
+[I 2025-12-18 05:52:23,500] Trial 1 finished with value: -1741.8932363755673 and parameters: {'embedding_dim': 417, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -1460.1246979043167.
+[I 2025-12-18 05:52:47,544] Trial 2 finished with value: -296.06123218613675 and parameters: {'embedding_dim': 296, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 2 with value: -296.06123218613675.
+[I 2025-12-18 05:53:17,581] Trial 3 finished with value: -797.8842164095561 and parameters: {'embedding_dim': 385, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 2 with value: -296.06123218613675.
+[I 2025-12-18 05:53:28,625] Trial 4 finished with value: -780.8587344762561 and parameters: {'embedding_dim': 232, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 2 with value: -296.06123218613675.
+[I 2025-12-18 05:54:39,368] Trial 5 finished with value: -991.8736213033901 and parameters: {'embedding_dim': 503, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 2 with value: -296.06123218613675.
+[I 2025-12-18 05:55:27,030] Trial 6 finished with value: -453.19712753746614 and parameters: {'embedding_dim': 496, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -296.06123218613675.
+[I 2025-12-18 05:55:41,096] Trial 7 finished with value: -1512.167701823795 and parameters: {'embedding_dim': 372, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 2 with value: -296.06123218613675.
+[I 2025-12-18 05:56:15,166] Trial 8 finished with value: -277.91800786408453 and parameters: {'embedding_dim': 430, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 8 with value: -277.91800786408453.
+[I 2025-12-18 05:56:30,705] Trial 9 finished with value: -676.4048042215389 and parameters: {'embedding_dim': 260, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 8 with value: -277.91800786408453.
+[I 2025-12-18 05:57:40,930] Trial 10 finished with value: -1272.0973253586935 and parameters: {'embedding_dim': 438, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 8 with value: -277.91800786408453.
+[I 2025-12-18 05:58:05,838] Trial 11 finished with value: -1445.1979213769457 and parameters: {'embedding_dim': 319, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 8 with value: -277.91800786408453.
+[I 2025-12-18 05:58:39,775] Trial 12 finished with value: -83.26327592251448 and parameters: {'embedding_dim': 298, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 12 with value: -83.26327592251448.
+[I 2025-12-18 05:59:16,628] Trial 13 finished with value: -379.4543221680915 and parameters: {'embedding_dim': 146, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 12 with value: -83.26327592251448.
+[I 2025-12-18 05:59:53,015] Trial 14 finished with value: -369.61265070960485 and parameters: {'embedding_dim': 352, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 12 with value: -83.26327592251448.
+[I 2025-12-18 06:00:29,250] Trial 15 finished with value: -791.2222722847432 and parameters: {'embedding_dim': 234, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 12 with value: -83.26327592251448.
+[I 2025-12-18 06:01:03,437] Trial 16 finished with value: -421.9442448036725 and parameters: {'embedding_dim': 453, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 12 with value: -83.26327592251448.
+[I 2025-12-18 06:02:04,174] Trial 17 finished with value: -665.7020794915035 and parameters: {'embedding_dim': 276, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 12 with value: -83.26327592251448.
+[I 2025-12-18 06:02:28,772] Trial 18 finished with value: -509.50428456059086 and parameters: {'embedding_dim': 337, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 12 with value: -83.26327592251448.
+[I 2025-12-18 06:02:45,267] Trial 19 finished with value: -502.6201337042212 and parameters: {'embedding_dim': 404, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 12 with value: -83.26327592251448.
+[I 2025-12-18 06:03:09,887] Trial 20 finished with value: -448.17456300276785 and parameters: {'embedding_dim': 471, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 12 with value: -83.26327592251448.
+[I 2025-12-18 06:03:33,446] Trial 21 finished with value: -964.9737400307226 and parameters: {'embedding_dim': 302, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 12 with value: -83.26327592251448.
+[I 2025-12-18 06:03:56,308] Trial 22 finished with value: -416.62428892233356 and parameters: {'embedding_dim': 289, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 12 with value: -83.26327592251448.
+[I 2025-12-18 06:04:33,193] Trial 23 finished with value: -1012.6885633368638 and parameters: {'embedding_dim': 208, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 12 with value: -83.26327592251448.
+[I 2025-12-18 06:05:10,340] Trial 24 finished with value: -551.5547562223667 and parameters: {'embedding_dim': 337, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 12 with value: -83.26327592251448.
+[I 2025-12-18 06:05:33,775] Trial 25 finished with value: -75.60396251007212 and parameters: {'embedding_dim': 256, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 25 with value: -75.60396251007212.
+[I 2025-12-18 06:06:07,326] Trial 26 finished with value: -2398.828282630014 and parameters: {'embedding_dim': 235, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 25 with value: -75.60396251007212.
+[I 2025-12-18 06:06:29,772] Trial 27 finished with value: -738.5800373159458 and parameters: {'embedding_dim': 193, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 25 with value: -75.60396251007212.
+[I 2025-12-18 06:06:51,587] Trial 28 finished with value: -801.1167616506505 and parameters: {'embedding_dim': 367, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 25 with value: -75.60396251007212.
+[I 2025-12-18 06:07:00,457] Trial 29 finished with value: -456.24906820138733 and parameters: {'embedding_dim': 150, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 25 with value: -75.60396251007212.
+[I 2025-12-18 06:07:24,389] A new study created in memory with name: no-name-dc70c5e8-0d1b-42c2-892b-d5fb30e9c9c1
+[I 2025-12-18 06:07:29,425] Trial 0 finished with value: -42.156565653790615 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -42.156565653790615.
+[I 2025-12-18 06:07:34,347] Trial 1 finished with value: -152.108837366538 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -42.156565653790615.
+[I 2025-12-18 06:07:39,930] Trial 2 finished with value: -42.914250414741005 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -42.156565653790615.
+[I 2025-12-18 06:07:43,201] Trial 3 finished with value: -51.704827961473164 and parameters: {'embedding_dim': 114, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -42.156565653790615.
+[I 2025-12-18 06:07:50,470] Trial 4 finished with value: -34.41792677170275 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 4 with value: -34.41792677170275.
+[I 2025-12-18 06:07:53,699] Trial 5 finished with value: -32.083117997759096 and parameters: {'embedding_dim': 108, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 5 with value: -32.083117997759096.
+[I 2025-12-18 06:08:00,222] Trial 6 finished with value: -55.00644103338647 and parameters: {'embedding_dim': 87, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 5 with value: -32.083117997759096.
+[I 2025-12-18 06:08:05,554] Trial 7 finished with value: -9.783759889833005 and parameters: {'embedding_dim': 76, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 7 with value: -9.783759889833005.
+[I 2025-12-18 06:08:10,575] Trial 8 finished with value: -16.677205277820796 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 7 with value: -9.783759889833005.
+[I 2025-12-18 06:08:17,797] Trial 9 finished with value: -53.16614012470307 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 7 with value: -9.783759889833005.
+[I 2025-12-18 06:08:21,260] Trial 10 finished with value: -64.95531983788986 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -9.783759889833005.
+[I 2025-12-18 06:08:26,300] Trial 11 finished with value: -113.36758081600298 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 7 with value: -9.783759889833005.
+[I 2025-12-18 06:08:31,330] Trial 12 finished with value: -32.555926618997994 and parameters: {'embedding_dim': 76, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 7 with value: -9.783759889833005.
+[I 2025-12-18 06:08:36,395] Trial 13 finished with value: -44.67072504122093 and parameters: {'embedding_dim': 121, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 7 with value: -9.783759889833005.
+[I 2025-12-18 06:08:39,866] Trial 14 finished with value: -51.255185606276534 and parameters: {'embedding_dim': 96, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -9.783759889833005.
+[I 2025-12-18 06:08:46,620] Trial 15 finished with value: -75.6774758935944 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 7 with value: -9.783759889833005.
+[I 2025-12-18 06:08:51,776] Trial 16 finished with value: -198.24475388538647 and parameters: {'embedding_dim': 65, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 7 with value: -9.783759889833005.
+[I 2025-12-18 06:08:55,246] Trial 17 finished with value: -53.74745668618681 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 7 with value: -9.783759889833005.
+[I 2025-12-18 06:09:02,431] Trial 18 finished with value: -24.684290622958635 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 7 with value: -9.783759889833005.
+[I 2025-12-18 06:09:07,478] Trial 19 finished with value: -68.71498283964873 and parameters: {'embedding_dim': 91, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 7 with value: -9.783759889833005.
+[I 2025-12-18 06:09:12,879] Trial 20 finished with value: -95.97225071744813 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 7 with value: -9.783759889833005.
+[I 2025-12-18 06:09:20,125] Trial 21 finished with value: -40.291127420780356 and parameters: {'embedding_dim': 115, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 7 with value: -9.783759889833005.
+[I 2025-12-18 06:09:27,408] Trial 22 finished with value: -20.504386418858704 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 7 with value: -9.783759889833005.
+[I 2025-12-18 06:09:34,740] Trial 23 finished with value: -23.627427338289067 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 7 with value: -9.783759889833005.
+[I 2025-12-18 06:09:40,304] Trial 24 finished with value: -2.682014606118458 and parameters: {'embedding_dim': 122, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:09:45,373] Trial 25 finished with value: -24.841783221153985 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:09:50,764] Trial 26 finished with value: -92.86782937936165 and parameters: {'embedding_dim': 122, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:09:56,148] Trial 27 finished with value: -21.753499728367636 and parameters: {'embedding_dim': 123, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:09:59,374] Trial 28 finished with value: -56.74418105399279 and parameters: {'embedding_dim': 80, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:10:04,421] Trial 29 finished with value: -46.587706164861515 and parameters: {'embedding_dim': 103, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:10:09,455] Trial 30 finished with value: -21.837106562790545 and parameters: {'embedding_dim': 70, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:10:14,792] Trial 31 finished with value: -61.54321534693137 and parameters: {'embedding_dim': 118, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:10:22,074] Trial 32 finished with value: -17.22061699348646 and parameters: {'embedding_dim': 110, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:10:27,410] Trial 33 finished with value: -27.9480252332801 and parameters: {'embedding_dim': 108, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:10:32,810] Trial 34 finished with value: -104.38184763035736 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:10:38,278] Trial 35 finished with value: -6.991163847369643 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:10:43,149] Trial 36 finished with value: -6.951915116616217 and parameters: {'embedding_dim': 85, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:10:48,041] Trial 37 finished with value: -90.58435082999041 and parameters: {'embedding_dim': 86, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:10:52,896] Trial 38 finished with value: -51.54621790207741 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:10:56,129] Trial 39 finished with value: -163.04525543021353 and parameters: {'embedding_dim': 80, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:11:00,961] Trial 40 finished with value: -161.88610719158 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:11:05,846] Trial 41 finished with value: -72.59079776889276 and parameters: {'embedding_dim': 95, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:11:10,696] Trial 42 finished with value: -59.88241850759454 and parameters: {'embedding_dim': 89, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:11:16,041] Trial 43 finished with value: -147.85468886604792 and parameters: {'embedding_dim': 94, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:11:21,375] Trial 44 finished with value: -57.59192098074729 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:11:26,496] Trial 45 finished with value: -26.511447342525848 and parameters: {'embedding_dim': 83, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:11:31,356] Trial 46 finished with value: -46.504858009634795 and parameters: {'embedding_dim': 77, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:11:36,683] Trial 47 finished with value: -111.58140647781751 and parameters: {'embedding_dim': 87, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:11:40,022] Trial 48 finished with value: -90.3528740822847 and parameters: {'embedding_dim': 104, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:11:45,386] Trial 49 finished with value: -23.26412149813363 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -2.682014606118458.
+[I 2025-12-18 06:11:50,980] A new study created in memory with name: no-name-29181b98-2ad6-4aa8-9230-c603d5c46e7c
+[I 2025-12-18 06:12:22,546] Trial 0 finished with value: -979.0652498162325 and parameters: {'embedding_dim': 316, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -979.0652498162325.
+[I 2025-12-18 06:12:46,132] Trial 1 finished with value: -633.8643566056994 and parameters: {'embedding_dim': 292, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -633.8643566056994.
+[I 2025-12-18 06:13:09,749] Trial 2 finished with value: -2895.1503321907326 and parameters: {'embedding_dim': 155, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 1 with value: -633.8643566056994.
+[I 2025-12-18 06:13:29,871] Trial 3 finished with value: -812.1216274470603 and parameters: {'embedding_dim': 461, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 1 with value: -633.8643566056994.
+[I 2025-12-18 06:13:45,469] Trial 4 finished with value: -408.42371839010883 and parameters: {'embedding_dim': 359, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 4 with value: -408.42371839010883.
+[I 2025-12-18 06:14:04,363] Trial 5 finished with value: -3546.8187244525075 and parameters: {'embedding_dim': 318, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 4 with value: -408.42371839010883.
+[I 2025-12-18 06:14:32,437] Trial 6 finished with value: -668.4386065017264 and parameters: {'embedding_dim': 359, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 4 with value: -408.42371839010883.
+[I 2025-12-18 06:14:50,921] Trial 7 finished with value: -463.41194432694226 and parameters: {'embedding_dim': 226, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 4 with value: -408.42371839010883.
+[I 2025-12-18 06:15:06,179] Trial 8 finished with value: -5656.6073486427385 and parameters: {'embedding_dim': 400, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 4 with value: -408.42371839010883.
+[I 2025-12-18 06:15:13,459] Trial 9 finished with value: -3861.428932404396 and parameters: {'embedding_dim': 183, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 4 with value: -408.42371839010883.
+[I 2025-12-18 06:15:29,677] Trial 10 finished with value: -849.8528782647024 and parameters: {'embedding_dim': 490, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 4 with value: -408.42371839010883.
+[I 2025-12-18 06:15:48,301] Trial 11 finished with value: -946.6640184919477 and parameters: {'embedding_dim': 214, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 4 with value: -408.42371839010883.
+[I 2025-12-18 06:16:05,311] Trial 12 finished with value: -1000.4271596619358 and parameters: {'embedding_dim': 249, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 4 with value: -408.42371839010883.
+[I 2025-12-18 06:16:21,402] Trial 13 finished with value: -1783.1658781451415 and parameters: {'embedding_dim': 407, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 4 with value: -408.42371839010883.
+[I 2025-12-18 06:16:40,439] Trial 14 finished with value: -1454.5628150390135 and parameters: {'embedding_dim': 249, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 4 with value: -408.42371839010883.
+[I 2025-12-18 06:16:56,888] Trial 15 finished with value: -1353.698162731182 and parameters: {'embedding_dim': 130, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 4 with value: -408.42371839010883.
+[I 2025-12-18 06:17:16,428] Trial 16 finished with value: -2305.4015506477645 and parameters: {'embedding_dim': 263, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 4 with value: -408.42371839010883.
+[I 2025-12-18 06:17:32,569] Trial 17 finished with value: -758.726242262552 and parameters: {'embedding_dim': 370, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 4 with value: -408.42371839010883.
+[I 2025-12-18 06:17:51,485] Trial 18 finished with value: -1142.746757420212 and parameters: {'embedding_dim': 196, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 4 with value: -408.42371839010883.
+[I 2025-12-18 06:18:11,837] Trial 19 finished with value: -464.97136450497135 and parameters: {'embedding_dim': 436, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 4 with value: -408.42371839010883.
+[I 2025-12-18 06:18:27,659] Trial 20 finished with value: -638.8978127156165 and parameters: {'embedding_dim': 361, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 4 with value: -408.42371839010883.
+[I 2025-12-18 06:18:47,728] Trial 21 finished with value: -151.84850952135736 and parameters: {'embedding_dim': 444, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 21 with value: -151.84850952135736.
+[I 2025-12-18 06:19:04,837] Trial 22 finished with value: -916.2961942923538 and parameters: {'embedding_dim': 456, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 21 with value: -151.84850952135736.
+[I 2025-12-18 06:19:24,431] Trial 23 finished with value: -224.20639632296798 and parameters: {'embedding_dim': 503, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 21 with value: -151.84850952135736.
+[I 2025-12-18 06:19:46,103] Trial 24 finished with value: -357.6716452439083 and parameters: {'embedding_dim': 479, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 21 with value: -151.84850952135736.
+[I 2025-12-18 06:20:05,895] Trial 25 finished with value: -518.6503462238489 and parameters: {'embedding_dim': 506, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 21 with value: -151.84850952135736.
+[I 2025-12-18 06:20:23,845] Trial 26 finished with value: -1194.5448158765687 and parameters: {'embedding_dim': 478, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 21 with value: -151.84850952135736.
+[I 2025-12-18 06:20:45,868] Trial 27 finished with value: -1180.1362770422782 and parameters: {'embedding_dim': 511, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 21 with value: -151.84850952135736.
+[I 2025-12-18 06:21:02,554] Trial 28 finished with value: -521.531270244104 and parameters: {'embedding_dim': 428, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 21 with value: -151.84850952135736.
+[I 2025-12-18 06:21:24,783] Trial 29 finished with value: -164.8510211069216 and parameters: {'embedding_dim': 474, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 21 with value: -151.84850952135736.
+[I 2025-12-18 06:21:44,914] A new study created in memory with name: no-name-8615e74a-3cd9-46c3-9f92-2c8d4168138a
+[I 2025-12-18 06:21:50,490] Trial 0 finished with value: -56.18295680922462 and parameters: {'embedding_dim': 73, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -56.18295680922462.
+[I 2025-12-18 06:21:59,063] Trial 1 finished with value: -122.82322112309265 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -56.18295680922462.
+[I 2025-12-18 06:22:03,914] Trial 2 finished with value: -30.569341579050455 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -30.569341579050455.
+[I 2025-12-18 06:22:07,057] Trial 3 finished with value: -25.979136290339902 and parameters: {'embedding_dim': 91, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:22:13,476] Trial 4 finished with value: -107.72249253356327 and parameters: {'embedding_dim': 74, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:22:19,886] Trial 5 finished with value: -132.8831150233621 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:22:23,136] Trial 6 finished with value: -335.1341082517222 and parameters: {'embedding_dim': 71, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:22:26,529] Trial 7 finished with value: -243.8386428408645 and parameters: {'embedding_dim': 88, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:22:35,212] Trial 8 finished with value: -124.53063416070515 and parameters: {'embedding_dim': 94, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:22:39,985] Trial 9 finished with value: -151.66433590227274 and parameters: {'embedding_dim': 88, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:22:43,383] Trial 10 finished with value: -277.55742205969267 and parameters: {'embedding_dim': 121, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:22:48,155] Trial 11 finished with value: -233.83587480037176 and parameters: {'embedding_dim': 111, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:22:51,313] Trial 12 finished with value: -150.09097370540718 and parameters: {'embedding_dim': 107, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:22:56,085] Trial 13 finished with value: -226.72597876496377 and parameters: {'embedding_dim': 106, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:22:59,218] Trial 14 finished with value: -393.58118002442575 and parameters: {'embedding_dim': 81, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:23:04,465] Trial 15 finished with value: -95.37779415566266 and parameters: {'embedding_dim': 100, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:23:07,623] Trial 16 finished with value: -279.03046494256245 and parameters: {'embedding_dim': 117, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:23:12,404] Trial 17 finished with value: -313.7890278170649 and parameters: {'embedding_dim': 65, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:23:15,978] Trial 18 finished with value: -51.479355120875795 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:23:23,774] Trial 19 finished with value: -105.35097950178806 and parameters: {'embedding_dim': 101, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:23:30,141] Trial 20 finished with value: -351.71605982833364 and parameters: {'embedding_dim': 81, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:23:33,536] Trial 21 finished with value: -119.19505002021712 and parameters: {'embedding_dim': 127, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:23:36,930] Trial 22 finished with value: -151.76963060683215 and parameters: {'embedding_dim': 116, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:23:40,307] Trial 23 finished with value: -114.09653593264454 and parameters: {'embedding_dim': 127, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:23:43,809] Trial 24 finished with value: -61.49335613269502 and parameters: {'embedding_dim': 83, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:23:47,285] Trial 25 finished with value: -395.11360460992535 and parameters: {'embedding_dim': 98, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:23:52,075] Trial 26 finished with value: -401.61786827735204 and parameters: {'embedding_dim': 105, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:23:56,244] Trial 27 finished with value: -186.8020396340978 and parameters: {'embedding_dim': 112, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:24:02,701] Trial 28 finished with value: -125.73777235287801 and parameters: {'embedding_dim': 122, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:24:06,213] Trial 29 finished with value: -158.0742236734061 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:24:11,205] Trial 30 finished with value: -176.24661514392108 and parameters: {'embedding_dim': 96, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:24:16,259] Trial 31 finished with value: -118.0568427336394 and parameters: {'embedding_dim': 66, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:24:22,786] Trial 32 finished with value: -243.14108769250845 and parameters: {'embedding_dim': 75, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:24:27,759] Trial 33 finished with value: -223.02016432527495 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:24:36,326] Trial 34 finished with value: -102.54611097334124 and parameters: {'embedding_dim': 71, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:24:41,284] Trial 35 finished with value: -114.84977977055274 and parameters: {'embedding_dim': 69, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:24:47,722] Trial 36 finished with value: -88.83192778422503 and parameters: {'embedding_dim': 92, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:24:52,520] Trial 37 finished with value: -162.3447500010564 and parameters: {'embedding_dim': 77, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:24:55,925] Trial 38 finished with value: -261.09313409998526 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:24:59,193] Trial 39 finished with value: -387.17553845957656 and parameters: {'embedding_dim': 78, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:25:06,424] Trial 40 finished with value: -202.07755802374567 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:25:11,506] Trial 41 finished with value: -268.1174545648371 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:25:14,900] Trial 42 finished with value: -438.117477736806 and parameters: {'embedding_dim': 84, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 3 with value: -25.979136290339902.
+[I 2025-12-18 06:25:18,345] Trial 43 finished with value: -18.875467911669023 and parameters: {'embedding_dim': 91, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 43 with value: -18.875467911669023.
+[I 2025-12-18 06:25:21,740] Trial 44 finished with value: -155.36038846421746 and parameters: {'embedding_dim': 91, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 43 with value: -18.875467911669023.
+[I 2025-12-18 06:25:25,138] Trial 45 finished with value: -218.25757654573596 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 43 with value: -18.875467911669023.
+[I 2025-12-18 06:25:29,910] Trial 46 finished with value: -358.3121765058688 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 43 with value: -18.875467911669023.
+[I 2025-12-18 06:25:33,039] Trial 47 finished with value: -508.349162365505 and parameters: {'embedding_dim': 97, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 43 with value: -18.875467911669023.
+[I 2025-12-18 06:25:38,290] Trial 48 finished with value: -21.15990562389633 and parameters: {'embedding_dim': 112, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 43 with value: -18.875467911669023.
+[I 2025-12-18 06:25:41,806] Trial 49 finished with value: -106.20807232044456 and parameters: {'embedding_dim': 123, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 43 with value: -18.875467911669023.
+[I 2025-12-18 06:25:45,651] A new study created in memory with name: no-name-dc75b520-b6e4-4e47-ab66-f4feb0e1dd00
+[I 2025-12-18 06:26:07,853] Trial 0 finished with value: -262.776000917663 and parameters: {'embedding_dim': 246, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 0 with value: -262.776000917663.
+[I 2025-12-18 06:26:22,694] Trial 1 finished with value: -547.9280142216338 and parameters: {'embedding_dim': 398, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -262.776000917663.
+[I 2025-12-18 06:26:38,809] Trial 2 finished with value: -394.62776314880284 and parameters: {'embedding_dim': 158, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 0 with value: -262.776000917663.
+[I 2025-12-18 06:26:52,645] Trial 3 finished with value: -165.1926689228908 and parameters: {'embedding_dim': 141, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 3 with value: -165.1926689228908.
+[I 2025-12-18 06:27:05,824] Trial 4 finished with value: -334.85893347263016 and parameters: {'embedding_dim': 310, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 3 with value: -165.1926689228908.
+[I 2025-12-18 06:27:19,329] Trial 5 finished with value: -2576.648494594691 and parameters: {'embedding_dim': 412, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 3 with value: -165.1926689228908.
+[I 2025-12-18 06:27:26,501] Trial 6 finished with value: -924.0474426535155 and parameters: {'embedding_dim': 352, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 3 with value: -165.1926689228908.
+[I 2025-12-18 06:27:42,818] Trial 7 finished with value: -230.01197601639365 and parameters: {'embedding_dim': 500, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 3 with value: -165.1926689228908.
+[I 2025-12-18 06:27:47,887] Trial 8 finished with value: -1037.3023218819515 and parameters: {'embedding_dim': 172, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 3 with value: -165.1926689228908.
+[I 2025-12-18 06:28:12,766] Trial 9 finished with value: -336.7292872670074 and parameters: {'embedding_dim': 461, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 3 with value: -165.1926689228908.
+[I 2025-12-18 06:28:21,626] Trial 10 finished with value: -405.42325341808095 and parameters: {'embedding_dim': 241, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 3 with value: -165.1926689228908.
+[I 2025-12-18 06:28:35,124] Trial 11 finished with value: -529.5512998422292 and parameters: {'embedding_dim': 505, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 3 with value: -165.1926689228908.
+[I 2025-12-18 06:28:51,501] Trial 12 finished with value: -287.0881079957109 and parameters: {'embedding_dim': 260, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 3 with value: -165.1926689228908.
+[I 2025-12-18 06:29:05,406] Trial 13 finished with value: -346.35010444815003 and parameters: {'embedding_dim': 144, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 3 with value: -165.1926689228908.
+[I 2025-12-18 06:29:18,971] Trial 14 finished with value: -295.88826520903393 and parameters: {'embedding_dim': 318, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 3 with value: -165.1926689228908.
+[I 2025-12-18 06:29:32,532] Trial 15 finished with value: -446.1279077003803 and parameters: {'embedding_dim': 508, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 3 with value: -165.1926689228908.
+[I 2025-12-18 06:29:43,579] Trial 16 finished with value: -402.0205158293214 and parameters: {'embedding_dim': 211, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 3 with value: -165.1926689228908.
+[I 2025-12-18 06:29:51,554] Trial 17 finished with value: -2157.103074548088 and parameters: {'embedding_dim': 397, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 3 with value: -165.1926689228908.
+[I 2025-12-18 06:30:09,807] Trial 18 finished with value: -236.0855962032249 and parameters: {'embedding_dim': 449, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 3 with value: -165.1926689228908.
+[I 2025-12-18 06:30:20,550] Trial 19 finished with value: -483.44780684185224 and parameters: {'embedding_dim': 286, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 3 with value: -165.1926689228908.
+[I 2025-12-18 06:30:31,679] Trial 20 finished with value: -558.8130852476105 and parameters: {'embedding_dim': 358, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 3 with value: -165.1926689228908.
+[I 2025-12-18 06:30:49,979] Trial 21 finished with value: -251.26582513839148 and parameters: {'embedding_dim': 472, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 3 with value: -165.1926689228908.
+[I 2025-12-18 06:31:06,401] Trial 22 finished with value: -82.3198350733116 and parameters: {'embedding_dim': 451, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 22 with value: -82.3198350733116.
+[I 2025-12-18 06:31:23,555] Trial 23 finished with value: -117.63238986539707 and parameters: {'embedding_dim': 425, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 22 with value: -82.3198350733116.
+[I 2025-12-18 06:31:37,043] Trial 24 finished with value: -463.1318594187459 and parameters: {'embedding_dim': 427, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 22 with value: -82.3198350733116.
+[I 2025-12-18 06:31:53,286] Trial 25 finished with value: -1159.5022209606484 and parameters: {'embedding_dim': 363, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 22 with value: -82.3198350733116.
+[I 2025-12-18 06:32:06,735] Trial 26 finished with value: -428.2654417208833 and parameters: {'embedding_dim': 381, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 22 with value: -82.3198350733116.
+[I 2025-12-18 06:32:23,005] Trial 27 finished with value: -269.46815021576697 and parameters: {'embedding_dim': 443, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 22 with value: -82.3198350733116.
+[I 2025-12-18 06:32:34,067] Trial 28 finished with value: -391.9702747110169 and parameters: {'embedding_dim': 198, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 22 with value: -82.3198350733116.
+[I 2025-12-18 06:32:52,533] Trial 29 finished with value: -318.2973668467731 and parameters: {'embedding_dim': 130, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 22 with value: -82.3198350733116.
+[I 2025-12-18 06:33:09,953] A new study created in memory with name: no-name-80869902-4e54-44e4-bd8c-59f59b9da599
+[I 2025-12-18 06:33:13,500] Trial 0 finished with value: -7.0128011166929705 and parameters: {'embedding_dim': 95, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -7.0128011166929705.
+[I 2025-12-18 06:33:18,552] Trial 1 finished with value: -35.02013951913533 and parameters: {'embedding_dim': 66, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 0 with value: -7.0128011166929705.
+[I 2025-12-18 06:33:25,310] Trial 2 finished with value: -160.11232170143484 and parameters: {'embedding_dim': 72, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -7.0128011166929705.
+[I 2025-12-18 06:33:28,730] Trial 3 finished with value: -38.43769425412794 and parameters: {'embedding_dim': 81, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 0 with value: -7.0128011166929705.
+[I 2025-12-18 06:33:32,488] Trial 4 finished with value: -119.01249006244664 and parameters: {'embedding_dim': 71, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -7.0128011166929705.
+[I 2025-12-18 06:33:38,944] Trial 5 finished with value: -59.35189255102644 and parameters: {'embedding_dim': 64, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -7.0128011166929705.
+[I 2025-12-18 06:33:44,229] Trial 6 finished with value: -79.4973809244134 and parameters: {'embedding_dim': 95, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -7.0128011166929705.
+[I 2025-12-18 06:33:53,737] Trial 7 finished with value: -94.48898640584412 and parameters: {'embedding_dim': 86, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 0 with value: -7.0128011166929705.
+[I 2025-12-18 06:33:58,829] Trial 8 finished with value: -180.79499387301308 and parameters: {'embedding_dim': 122, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -7.0128011166929705.
+[I 2025-12-18 06:34:03,945] Trial 9 finished with value: -303.37855736032924 and parameters: {'embedding_dim': 77, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 0 with value: -7.0128011166929705.
+[I 2025-12-18 06:34:07,487] Trial 10 finished with value: -266.0467114981943 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -7.0128011166929705.
+[I 2025-12-18 06:34:10,790] Trial 11 finished with value: -201.9896490222263 and parameters: {'embedding_dim': 106, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -7.0128011166929705.
+[I 2025-12-18 06:34:16,192] Trial 12 finished with value: -60.952755687204075 and parameters: {'embedding_dim': 94, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -7.0128011166929705.
+[I 2025-12-18 06:34:19,477] Trial 13 finished with value: -122.18442617550512 and parameters: {'embedding_dim': 103, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 0 with value: -7.0128011166929705.
+[I 2025-12-18 06:34:24,901] Trial 14 finished with value: -24.329833917348186 and parameters: {'embedding_dim': 127, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -7.0128011166929705.
+[I 2025-12-18 06:34:28,573] Trial 15 finished with value: -358.12592985202144 and parameters: {'embedding_dim': 124, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 0 with value: -7.0128011166929705.
+[I 2025-12-18 06:34:36,842] Trial 16 finished with value: -3.8492300168743543 and parameters: {'embedding_dim': 108, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 16 with value: -3.8492300168743543.
+[I 2025-12-18 06:34:46,040] Trial 17 finished with value: -73.51799746212957 and parameters: {'embedding_dim': 106, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 16 with value: -3.8492300168743543.
+[I 2025-12-18 06:34:53,547] Trial 18 finished with value: -30.76274838169608 and parameters: {'embedding_dim': 116, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 16 with value: -3.8492300168743543.
+[I 2025-12-18 06:35:00,850] Trial 19 finished with value: -10.325870859065535 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 16 with value: -3.8492300168743543.
+[I 2025-12-18 06:35:08,279] Trial 20 finished with value: -70.15212089974422 and parameters: {'embedding_dim': 101, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 16 with value: -3.8492300168743543.
+[I 2025-12-18 06:35:15,553] Trial 21 finished with value: -121.47274766305733 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 16 with value: -3.8492300168743543.
+[I 2025-12-18 06:35:22,930] Trial 22 finished with value: -200.9863930297234 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 16 with value: -3.8492300168743543.
+[I 2025-12-18 06:35:30,208] Trial 23 finished with value: -126.63925421420936 and parameters: {'embedding_dim': 111, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 16 with value: -3.8492300168743543.
+[I 2025-12-18 06:35:37,472] Trial 24 finished with value: -66.29256414657428 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 16 with value: -3.8492300168743543.
+[I 2025-12-18 06:35:44,726] Trial 25 finished with value: -19.848337031443283 and parameters: {'embedding_dim': 99, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 16 with value: -3.8492300168743543.
+[I 2025-12-18 06:35:50,091] Trial 26 finished with value: -15.522721167063033 and parameters: {'embedding_dim': 82, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 16 with value: -3.8492300168743543.
+[I 2025-12-18 06:35:57,326] Trial 27 finished with value: -20.59384036060435 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 16 with value: -3.8492300168743543.
+[I 2025-12-18 06:36:00,842] Trial 28 finished with value: -18.42064237756656 and parameters: {'embedding_dim': 109, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 16 with value: -3.8492300168743543.
+[I 2025-12-18 06:36:08,672] Trial 29 finished with value: -3.427730241226805 and parameters: {'embedding_dim': 88, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 29 with value: -3.427730241226805.
+[I 2025-12-18 06:36:13,640] Trial 30 finished with value: -30.056436788319996 and parameters: {'embedding_dim': 118, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 29 with value: -3.427730241226805.
+[I 2025-12-18 06:36:20,236] Trial 31 finished with value: -1.8860202357743814 and parameters: {'embedding_dim': 90, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 31 with value: -1.8860202357743814.
+[I 2025-12-18 06:36:25,187] Trial 32 finished with value: -16.89330148627998 and parameters: {'embedding_dim': 84, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 31 with value: -1.8860202357743814.
+[I 2025-12-18 06:36:30,134] Trial 33 finished with value: -146.77499489663052 and parameters: {'embedding_dim': 77, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 31 with value: -1.8860202357743814.
+[I 2025-12-18 06:36:33,430] Trial 34 finished with value: -55.44491881513177 and parameters: {'embedding_dim': 104, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 31 with value: -1.8860202357743814.
+[I 2025-12-18 06:36:39,998] Trial 35 finished with value: -49.84524120139588 and parameters: {'embedding_dim': 92, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 31 with value: -1.8860202357743814.
+[I 2025-12-18 06:36:43,305] Trial 36 finished with value: -114.45469134729363 and parameters: {'embedding_dim': 69, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 31 with value: -1.8860202357743814.
+[I 2025-12-18 06:36:49,771] Trial 37 finished with value: -83.99617259583106 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 31 with value: -1.8860202357743814.
+[I 2025-12-18 06:36:54,699] Trial 38 finished with value: -48.23489465441547 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 31 with value: -1.8860202357743814.
+[I 2025-12-18 06:37:01,528] Trial 39 finished with value: -225.69376767129577 and parameters: {'embedding_dim': 87, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 31 with value: -1.8860202357743814.
+[I 2025-12-18 06:37:05,889] Trial 40 finished with value: -137.56719040701063 and parameters: {'embedding_dim': 91, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 31 with value: -1.8860202357743814.
+[I 2025-12-18 06:37:14,963] Trial 41 finished with value: -10.55925944861275 and parameters: {'embedding_dim': 85, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 31 with value: -1.8860202357743814.
+[I 2025-12-18 06:37:21,938] Trial 42 finished with value: -281.7966910189318 and parameters: {'embedding_dim': 96, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 31 with value: -1.8860202357743814.
+[I 2025-12-18 06:37:28,644] Trial 43 finished with value: -264.3647471400428 and parameters: {'embedding_dim': 89, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 31 with value: -1.8860202357743814.
+[I 2025-12-18 06:37:35,931] Trial 44 finished with value: -25.75026465231285 and parameters: {'embedding_dim': 73, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 31 with value: -1.8860202357743814.
+[I 2025-12-18 06:37:42,520] Trial 45 finished with value: -36.36570565744985 and parameters: {'embedding_dim': 82, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 31 with value: -1.8860202357743814.
+[I 2025-12-18 06:37:47,567] Trial 46 finished with value: -25.4697360903644 and parameters: {'embedding_dim': 94, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 31 with value: -1.8860202357743814.
+[I 2025-12-18 06:37:56,296] Trial 47 finished with value: -127.2787639074129 and parameters: {'embedding_dim': 101, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 31 with value: -1.8860202357743814.
+[I 2025-12-18 06:38:02,046] Trial 48 finished with value: -246.85407984690568 and parameters: {'embedding_dim': 87, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 1}. Best is trial 31 with value: -1.8860202357743814.
+[I 2025-12-18 06:38:07,460] Trial 49 finished with value: -284.35726806707623 and parameters: {'embedding_dim': 74, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 31 with value: -1.8860202357743814.
+[I 2025-12-18 06:38:14,621] A new study created in memory with name: no-name-13afcc68-9f0d-46a0-9a2c-943ce5e8e19a
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_20000_3_seoul_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_20000_3_seoul_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan20000_3_seoul.csv: Class 0=15889 | Class 1=17325
+Saved ../../data/data_oversampled/ctgan20000/ctgan20000_3_seoul.csv: Class 0=15905 | Class 1=18980 | Class 2=15873
+Processing ../../data/data_for_modeling/busan_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/busan_train.csv: Optimizing CTGAN for class 1...
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_20000_3_busan_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_20000_3_busan_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan20000_3_busan.csv: Class 0=18886 | Class 1=17076
+Saved ../../data/data_oversampled/ctgan20000/ctgan20000_3_busan.csv: Class 0=18946 | Class 1=18121 | Class 2=16439
+Processing ../../data/data_for_modeling/daegu_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/daegu_train.csv: Optimizing CTGAN for class 1...
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_20000_3_daegu_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_20000_3_daegu_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan20000_3_daegu.csv: Class 0=15168 | Class 1=17954
+Saved ../../data/data_oversampled/ctgan20000/ctgan20000_3_daegu.csv: Class 0=15201 | Class 1=18552 | Class 2=16913
+Processing ../../data/data_for_modeling/daejeon_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/daejeon_train.csv: Optimizing CTGAN for class 1...
+[I 2025-12-18 06:38:28,602] Trial 0 finished with value: -876.4887042191933 and parameters: {'embedding_dim': 230, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 0 with value: -876.4887042191933.
+[I 2025-12-18 06:38:48,717] Trial 1 finished with value: -238.44076333441086 and parameters: {'embedding_dim': 238, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 1 with value: -238.44076333441086.
+[I 2025-12-18 06:39:14,633] Trial 2 finished with value: -613.6193318323284 and parameters: {'embedding_dim': 390, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 1 with value: -238.44076333441086.
+[I 2025-12-18 06:40:28,017] Trial 3 finished with value: -477.3427260148117 and parameters: {'embedding_dim': 137, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 1 with value: -238.44076333441086.
+[I 2025-12-18 06:40:49,791] Trial 4 finished with value: -2424.0170394468723 and parameters: {'embedding_dim': 494, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 1 with value: -238.44076333441086.
+[I 2025-12-18 06:41:33,494] Trial 5 finished with value: -208.3972467079355 and parameters: {'embedding_dim': 442, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 5 with value: -208.3972467079355.
+[I 2025-12-18 06:41:48,043] Trial 6 finished with value: -793.7630358397654 and parameters: {'embedding_dim': 487, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 5 with value: -208.3972467079355.
+[I 2025-12-18 06:42:09,461] Trial 7 finished with value: -304.8168467569619 and parameters: {'embedding_dim': 420, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 5 with value: -208.3972467079355.
+[I 2025-12-18 06:42:31,842] Trial 8 finished with value: -249.82410614908883 and parameters: {'embedding_dim': 155, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 5 with value: -208.3972467079355.
+[I 2025-12-18 06:42:43,568] Trial 9 finished with value: -856.3293330866918 and parameters: {'embedding_dim': 500, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 2}. Best is trial 5 with value: -208.3972467079355.
+[I 2025-12-18 06:43:48,410] Trial 10 finished with value: -225.0848165505214 and parameters: {'embedding_dim': 347, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 5 with value: -208.3972467079355.
+[I 2025-12-18 06:44:49,480] Trial 11 finished with value: -979.6343439717962 and parameters: {'embedding_dim': 347, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 5 with value: -208.3972467079355.
+[I 2025-12-18 06:45:46,386] Trial 12 finished with value: -1495.2456257075962 and parameters: {'embedding_dim': 310, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 5 with value: -208.3972467079355.
+[I 2025-12-18 06:46:43,594] Trial 13 finished with value: -318.73739234910704 and parameters: {'embedding_dim': 420, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 5 with value: -208.3972467079355.
+[I 2025-12-18 06:47:11,288] Trial 14 finished with value: -647.8217842206632 and parameters: {'embedding_dim': 308, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 5 with value: -208.3972467079355.
+[I 2025-12-18 06:48:09,248] Trial 15 finished with value: -613.4184733591193 and parameters: {'embedding_dim': 366, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 5 with value: -208.3972467079355.
+[I 2025-12-18 06:48:38,117] Trial 16 finished with value: -1760.9965125999818 and parameters: {'embedding_dim': 444, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 5 with value: -208.3972467079355.
+[I 2025-12-18 06:49:12,723] Trial 17 finished with value: -913.3404575112572 and parameters: {'embedding_dim': 282, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 5 with value: -208.3972467079355.
+[I 2025-12-18 06:50:21,088] Trial 18 finished with value: -883.1538379419289 and parameters: {'embedding_dim': 447, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 5 with value: -208.3972467079355.
+[I 2025-12-18 06:50:48,452] Trial 19 finished with value: -396.6025136759164 and parameters: {'embedding_dim': 369, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 5 with value: -208.3972467079355.
+[I 2025-12-18 06:51:44,972] Trial 20 finished with value: -2283.3483549473526 and parameters: {'embedding_dim': 275, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 5 with value: -208.3972467079355.
+[I 2025-12-18 06:52:04,752] Trial 21 finished with value: -413.74389669661093 and parameters: {'embedding_dim': 225, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 5 with value: -208.3972467079355.
+[I 2025-12-18 06:52:24,756] Trial 22 finished with value: -314.808855760333 and parameters: {'embedding_dim': 211, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 5 with value: -208.3972467079355.
+[I 2025-12-18 06:52:44,881] Trial 23 finished with value: -135.31685155902102 and parameters: {'embedding_dim': 196, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 23 with value: -135.31685155902102.
+[I 2025-12-18 06:53:42,349] Trial 24 finished with value: -286.66437501838396 and parameters: {'embedding_dim': 181, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 23 with value: -135.31685155902102.
+[I 2025-12-18 06:54:01,774] Trial 25 finished with value: -658.3790023755494 and parameters: {'embedding_dim': 271, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 23 with value: -135.31685155902102.
+[I 2025-12-18 06:54:36,459] Trial 26 finished with value: -303.3501382061561 and parameters: {'embedding_dim': 332, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 23 with value: -135.31685155902102.
+[I 2025-12-18 06:55:18,087] Trial 27 finished with value: -385.7101890789343 and parameters: {'embedding_dim': 465, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 23 with value: -135.31685155902102.
+[I 2025-12-18 06:56:15,151] Trial 28 finished with value: -424.09289485932004 and parameters: {'embedding_dim': 403, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 23 with value: -135.31685155902102.
+[I 2025-12-18 06:56:23,529] Trial 29 finished with value: -3590.342543134422 and parameters: {'embedding_dim': 198, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 1}. Best is trial 23 with value: -135.31685155902102.
+[I 2025-12-18 06:56:44,528] A new study created in memory with name: no-name-d28bd8e7-1b2a-4390-b22f-c9b616f56d4b
+[I 2025-12-18 06:56:51,631] Trial 0 finished with value: -16.926240168014512 and parameters: {'embedding_dim': 123, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 0 with value: -16.926240168014512.
+[I 2025-12-18 06:56:58,143] Trial 1 finished with value: -294.01281727298465 and parameters: {'embedding_dim': 64, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 0 with value: -16.926240168014512.
+[I 2025-12-18 06:57:04,918] Trial 2 finished with value: -11.345157142983446 and parameters: {'embedding_dim': 115, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -11.345157142983446.
+[I 2025-12-18 06:57:11,389] Trial 3 finished with value: -330.54109312554044 and parameters: {'embedding_dim': 84, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -11.345157142983446.
+[I 2025-12-18 06:57:16,478] Trial 4 finished with value: -229.76026419998485 and parameters: {'embedding_dim': 65, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -11.345157142983446.
+[I 2025-12-18 06:57:23,892] Trial 5 finished with value: -97.28066376578207 and parameters: {'embedding_dim': 126, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -11.345157142983446.
+[I 2025-12-18 06:57:27,255] Trial 6 finished with value: -29.41362580478605 and parameters: {'embedding_dim': 128, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -11.345157142983446.
+[I 2025-12-18 06:57:32,096] Trial 7 finished with value: -65.0845515113347 and parameters: {'embedding_dim': 102, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 2 with value: -11.345157142983446.
+[I 2025-12-18 06:57:38,567] Trial 8 finished with value: -170.93450677654076 and parameters: {'embedding_dim': 128, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 2 with value: -11.345157142983446.
+[I 2025-12-18 06:57:45,285] Trial 9 finished with value: -91.2084308906854 and parameters: {'embedding_dim': 86, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 2 with value: -11.345157142983446.
+[I 2025-12-18 06:57:48,569] Trial 10 finished with value: -84.353342726977 and parameters: {'embedding_dim': 109, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -11.345157142983446.
+[I 2025-12-18 06:57:53,933] Trial 11 finished with value: -38.61296092906559 and parameters: {'embedding_dim': 113, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -11.345157142983446.
+[I 2025-12-18 06:58:01,155] Trial 12 finished with value: -146.97459549462454 and parameters: {'embedding_dim': 113, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -11.345157142983446.
+[I 2025-12-18 06:58:06,517] Trial 13 finished with value: -253.40271088516624 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 2 with value: -11.345157142983446.
+[I 2025-12-18 06:58:13,784] Trial 14 finished with value: -106.42064597413244 and parameters: {'embedding_dim': 95, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 2 with value: -11.345157142983446.
+[I 2025-12-18 06:58:18,917] Trial 15 finished with value: -12.449332817438894 and parameters: {'embedding_dim': 103, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -11.345157142983446.
+[I 2025-12-18 06:58:22,232] Trial 16 finished with value: -145.14767066461988 and parameters: {'embedding_dim': 97, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -11.345157142983446.
+[I 2025-12-18 06:58:27,166] Trial 17 finished with value: -25.523613254187588 and parameters: {'embedding_dim': 106, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -11.345157142983446.
+[I 2025-12-18 06:58:32,254] Trial 18 finished with value: -78.07353082716638 and parameters: {'embedding_dim': 86, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -11.345157142983446.
+[I 2025-12-18 06:58:35,672] Trial 19 finished with value: -106.36845311978671 and parameters: {'embedding_dim': 118, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 2 with value: -11.345157142983446.
+[I 2025-12-18 06:58:40,691] Trial 20 finished with value: -14.370737133315647 and parameters: {'embedding_dim': 94, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -11.345157142983446.
+[I 2025-12-18 06:58:45,707] Trial 21 finished with value: -192.5413504975833 and parameters: {'embedding_dim': 94, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -11.345157142983446.
+[I 2025-12-18 06:58:50,719] Trial 22 finished with value: -272.03390310688116 and parameters: {'embedding_dim': 102, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -11.345157142983446.
+[I 2025-12-18 06:58:55,766] Trial 23 finished with value: -49.811973468399856 and parameters: {'embedding_dim': 93, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 2 with value: -11.345157142983446.
+[I 2025-12-18 06:59:00,788] Trial 24 finished with value: -6.672102821167573 and parameters: {'embedding_dim': 79, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 06:59:04,084] Trial 25 finished with value: -79.77148046169478 and parameters: {'embedding_dim': 77, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 06:59:09,089] Trial 26 finished with value: -35.35250027457312 and parameters: {'embedding_dim': 69, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 06:59:14,121] Trial 27 finished with value: -346.67461500282207 and parameters: {'embedding_dim': 81, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 06:59:19,337] Trial 28 finished with value: -299.58432973875637 and parameters: {'embedding_dim': 72, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 06:59:25,873] Trial 29 finished with value: -40.95015021403158 and parameters: {'embedding_dim': 119, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 06:59:30,904] Trial 30 finished with value: -117.99122630649329 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 06:59:35,948] Trial 31 finished with value: -99.12310344381473 and parameters: {'embedding_dim': 90, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 06:59:40,872] Trial 32 finished with value: -44.03870475694802 and parameters: {'embedding_dim': 107, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 06:59:45,817] Trial 33 finished with value: -81.98550495527074 and parameters: {'embedding_dim': 77, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 06:59:52,463] Trial 34 finished with value: -34.87531075869889 and parameters: {'embedding_dim': 112, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 06:59:57,537] Trial 35 finished with value: -99.20620785128071 and parameters: {'embedding_dim': 90, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 07:00:04,332] Trial 36 finished with value: -171.91541911458992 and parameters: {'embedding_dim': 122, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 3}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 07:00:07,596] Trial 37 finished with value: -250.04769042965705 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 07:00:12,675] Trial 38 finished with value: -75.18011134040808 and parameters: {'embedding_dim': 81, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 07:00:19,202] Trial 39 finished with value: -170.518364570785 and parameters: {'embedding_dim': 100, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 3}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 07:00:24,534] Trial 40 finished with value: -10.885030493215972 and parameters: {'embedding_dim': 109, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 07:00:29,862] Trial 41 finished with value: -49.34810617787086 and parameters: {'embedding_dim': 110, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 07:00:35,204] Trial 42 finished with value: -114.96687683399969 and parameters: {'embedding_dim': 115, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 07:00:40,575] Trial 43 finished with value: -116.72854882533255 and parameters: {'embedding_dim': 123, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 07:00:45,925] Trial 44 finished with value: -20.88441772590685 and parameters: {'embedding_dim': 108, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 07:00:51,283] Trial 45 finished with value: -163.19875002229307 and parameters: {'embedding_dim': 98, 'generator_dim': (64, 64), 'discriminator_dim': (64, 64), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 07:00:56,154] Trial 46 finished with value: -18.41979092626437 and parameters: {'embedding_dim': 104, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 64, 'discriminator_steps': 2}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 07:01:03,346] Trial 47 finished with value: -26.10283520864332 and parameters: {'embedding_dim': 114, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 3}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 07:01:06,664] Trial 48 finished with value: -210.40004338215854 and parameters: {'embedding_dim': 117, 'generator_dim': (128, 128), 'discriminator_dim': (64, 64), 'pac': 8, 'batch_size': 128, 'discriminator_steps': 1}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 07:01:11,731] Trial 49 finished with value: -131.5807178408482 and parameters: {'embedding_dim': 90, 'generator_dim': (64, 64), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 128, 'discriminator_steps': 2}. Best is trial 24 with value: -6.672102821167573.
+[I 2025-12-18 07:01:17,114] A new study created in memory with name: no-name-c639bc21-d073-45fc-a565-000779e7de22
+[I 2025-12-18 07:01:45,503] Trial 0 finished with value: -1830.3249297278587 and parameters: {'embedding_dim': 277, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 0 with value: -1830.3249297278587.
+[I 2025-12-18 07:02:04,771] Trial 1 finished with value: -1298.324721908804 and parameters: {'embedding_dim': 133, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 256, 'discriminator_steps': 1}. Best is trial 1 with value: -1298.324721908804.
+[I 2025-12-18 07:02:24,399] Trial 2 finished with value: -474.04994392373914 and parameters: {'embedding_dim': 348, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 1024, 'discriminator_steps': 5}. Best is trial 2 with value: -474.04994392373914.
+[I 2025-12-18 07:03:21,371] Trial 3 finished with value: -2120.1556228752374 and parameters: {'embedding_dim': 356, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 5}. Best is trial 2 with value: -474.04994392373914.
+[I 2025-12-18 07:04:09,008] Trial 4 finished with value: -782.0892025975137 and parameters: {'embedding_dim': 378, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 4}. Best is trial 2 with value: -474.04994392373914.
+[I 2025-12-18 07:04:19,561] Trial 5 finished with value: -2010.6068235936493 and parameters: {'embedding_dim': 403, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 1}. Best is trial 2 with value: -474.04994392373914.
+[I 2025-12-18 07:04:48,529] Trial 6 finished with value: -437.2094598521286 and parameters: {'embedding_dim': 298, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 6 with value: -437.2094598521286.
+[I 2025-12-18 07:05:17,703] Trial 7 finished with value: -10674.219478575118 and parameters: {'embedding_dim': 343, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 256, 'discriminator_steps': 2}. Best is trial 6 with value: -437.2094598521286.
+[I 2025-12-18 07:05:46,070] Trial 8 finished with value: -1775.5873652779092 and parameters: {'embedding_dim': 356, 'generator_dim': (256, 256), 'discriminator_dim': (128, 128), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 6 with value: -437.2094598521286.
+[I 2025-12-18 07:06:15,015] Trial 9 finished with value: -727.6710560207903 and parameters: {'embedding_dim': 490, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 8, 'batch_size': 512, 'discriminator_steps': 5}. Best is trial 6 with value: -437.2094598521286.
+[I 2025-12-18 07:06:28,743] Trial 10 finished with value: -464.935845640714 and parameters: {'embedding_dim': 228, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 6 with value: -437.2094598521286.
+[I 2025-12-18 07:06:42,150] Trial 11 finished with value: -440.91438284199035 and parameters: {'embedding_dim': 246, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 6 with value: -437.2094598521286.
+[I 2025-12-18 07:06:56,028] Trial 12 finished with value: -810.7504409180672 and parameters: {'embedding_dim': 224, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 3}. Best is trial 6 with value: -437.2094598521286.
+[I 2025-12-18 07:07:16,950] Trial 13 finished with value: -598.90636520583 and parameters: {'embedding_dim': 259, 'generator_dim': (128, 128), 'discriminator_dim': (128, 128), 'pac': 4, 'batch_size': 1024, 'discriminator_steps': 4}. Best is trial 6 with value: -437.2094598521286.
+[I 2025-12-18 07:07:41,569] Trial 14 finished with value: -385.64721044260756 and parameters: {'embedding_dim': 164, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 14 with value: -385.64721044260756.
+[I 2025-12-18 07:08:09,907] Trial 15 finished with value: -67.45913713148555 and parameters: {'embedding_dim': 130, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 15 with value: -67.45913713148555.
+[I 2025-12-18 07:08:35,602] Trial 16 finished with value: -833.7291688961906 and parameters: {'embedding_dim': 135, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 15 with value: -67.45913713148555.
+[I 2025-12-18 07:08:59,809] Trial 17 finished with value: -161.75823376664331 and parameters: {'embedding_dim': 182, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 15 with value: -67.45913713148555.
+[I 2025-12-18 07:09:25,422] Trial 18 finished with value: -1341.782662517804 and parameters: {'embedding_dim': 188, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 15 with value: -67.45913713148555.
+[I 2025-12-18 07:09:40,949] Trial 19 finished with value: -272.5528182061766 and parameters: {'embedding_dim': 191, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 15 with value: -67.45913713148555.
+[I 2025-12-18 07:10:00,594] Trial 20 finished with value: -509.4221494464748 and parameters: {'embedding_dim': 182, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 15 with value: -67.45913713148555.
+[I 2025-12-18 07:10:18,359] Trial 21 finished with value: -543.4652825350722 and parameters: {'embedding_dim': 204, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 15 with value: -67.45913713148555.
+[I 2025-12-18 07:10:34,421] Trial 22 finished with value: -628.6674229110847 and parameters: {'embedding_dim': 128, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 2}. Best is trial 15 with value: -67.45913713148555.
+[I 2025-12-18 07:11:01,930] Trial 23 finished with value: -228.91513954093193 and parameters: {'embedding_dim': 163, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 15 with value: -67.45913713148555.
+[I 2025-12-18 07:11:26,440] Trial 24 finished with value: -405.4265603260346 and parameters: {'embedding_dim': 160, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 15 with value: -67.45913713148555.
+[I 2025-12-18 07:11:51,255] Trial 25 finished with value: -209.19742257256502 and parameters: {'embedding_dim': 163, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 15 with value: -67.45913713148555.
+[I 2025-12-18 07:12:16,442] Trial 26 finished with value: -237.0986743435795 and parameters: {'embedding_dim': 447, 'generator_dim': (256, 256), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 15 with value: -67.45913713148555.
+[I 2025-12-18 07:12:38,032] Trial 27 finished with value: -745.8323636940028 and parameters: {'embedding_dim': 217, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 15 with value: -67.45913713148555.
+[I 2025-12-18 07:13:04,783] Trial 28 finished with value: -889.1171137565198 and parameters: {'embedding_dim': 295, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 4}. Best is trial 15 with value: -67.45913713148555.
+[I 2025-12-18 07:13:23,913] Trial 29 finished with value: -244.75040597105453 and parameters: {'embedding_dim': 259, 'generator_dim': (128, 128), 'discriminator_dim': (256, 256), 'pac': 4, 'batch_size': 512, 'discriminator_steps': 3}. Best is trial 15 with value: -67.45913713148555.
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_20000_3_daejeon_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_20000_3_daejeon_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan20000_3_daejeon.csv: Class 0=17535 | Class 1=16659
+Saved ../../data/data_oversampled/ctgan20000/ctgan20000_3_daejeon.csv: Class 0=17620 | Class 1=18334 | Class 2=15784
+Processing ../../data/data_for_modeling/gwangju_train.csv: Optimizing CTGAN for class 0...
+Processing ../../data/data_for_modeling/gwangju_train.csv: Optimizing CTGAN for class 1...
+Saved CTGAN model for class 0: ../save_model/oversampling_models/ctgan_only_20000_3_gwangju_class0.pkl
+Saved CTGAN model for class 1: ../save_model/oversampling_models/ctgan_only_20000_3_gwangju_class1.pkl
+Saved augmented data only ../../data/data_oversampled/augmented_only/ctgan20000_3_gwangju.csv: Class 0=17686 | Class 1=17465
+Saved ../../data/data_oversampled/ctgan20000/ctgan20000_3_gwangju.csv: Class 0=17737 | Class 1=18814 | Class 2=16144
+
+==========================================
+All CTGAN sample generation completed!
+==========================================