Update range

Signed-off-by: Aadhitya A <[email protected]>

app.py

@@ -555,13 +555,13 @@ def modelTFT(csv_file, prax):
             model_path="optuna_test",
             n_trials=5,
             max_epochs=MAX_EPOCHS,
-            gradient_clip_val_range=(0.01, 0.5),
-            hidden_size_range=(8, 64),
-            hidden_continuous_size_range=(8, 24),
-            attention_head_size_range=(1, 4),
-            learning_rate_range=(0.01, 0.1),
-            dropout_range=(0.1, 0.3),
-            trainer_kwargs=dict(limit_train_batches=30),
+            gradient_clip_val_range=(0.01, 0.3),
+            hidden_size_range=(8, 24),
+            hidden_continuous_size_range=(8, 12),
+            attention_head_size_range=(2, 4),
+            learning_rate_range=(0.01, 0.05),
+            dropout_range=(0.1, 0.25),
+            trainer_kwargs=dict(limit_train_batches=20),
             reduce_on_plateau_patience=4,
             pruner=optuna.pruners.MedianPruner(n_min_trials=3, n_startup_trials=3),
             use_learning_rate_finder=False,  # use Optuna to find ideal learning rate or use in-built learning rate finder
@@ -787,13 +787,13 @@ def modelTFT_OpenGap(csv_file, prax):
             model_path="optuna_test",
             n_trials=5,
             max_epochs=MAX_EPOCHS,
-            gradient_clip_val_range=(0.01, 0.5),
-            hidden_size_range=(8, 64),
-            hidden_continuous_size_range=(8, 24),
-            attention_head_size_range=(1, 4),
-            learning_rate_range=(0.01, 0.1),
-            dropout_range=(0.1, 0.3),
-            trainer_kwargs=dict(limit_train_batches=30),
+            gradient_clip_val_range=(0.01, 0.3),
+            hidden_size_range=(8, 24),
+            hidden_continuous_size_range=(8, 12),
+            attention_head_size_range=(2, 4),
+            learning_rate_range=(0.01, 0.05),
+            dropout_range=(0.1, 0.25),
+            trainer_kwargs=dict(limit_train_batches=20),
             reduce_on_plateau_patience=4,
             pruner=optuna.pruners.MedianPruner(n_min_trials=3, n_warmup_steps=3),
             use_learning_rate_finder=False,  # use Optuna to find ideal learning rate or use in-built learning rate finder