diff --git a/openfe/FeatureSelector.py b/openfe/FeatureSelector.py
index b0e7337..7636a42 100644
--- a/openfe/FeatureSelector.py
+++ b/openfe/FeatureSelector.py
@@ -234,7 +234,7 @@ def get_metric(self):
 
     def get_estimator(self):
         if self.estimator is None:
-            params = {'n_jobs': self.n_jobs, 'importance_type': 'gain', 'n_estimators': 200, "verbose": 1 if self.verbose else -1 }
+            params = {'n_jobs': self.n_jobs, 'importance_type': 'gain', 'n_estimators': 200, "verbose": -1 }
             if self.task == 'classification':
                 self.estimator = lgb.LGBMClassifier(**params)
             else:
@@ -530,7 +530,7 @@ def stage2_select(self):
         self.myprint("Finish data processing.")
         if self.stage2_params is None:
             params = {"n_estimators": 1000, "importance_type": "gain", "num_leaves": 16,
-                      "seed": 1, "n_jobs": self.n_jobs, "verbose": 1 if self.verbose else -1}
+                      "seed": 1, "n_jobs": self.n_jobs, "verbose": -1}
         else:
             params = self.stage2_params
         if self.metric is not None:
@@ -609,7 +609,7 @@ def _evaluate(self, data_temp, candidate_feature, train_y, val_y, train_init, va
             val_x = pd.DataFrame(data_temp[candidate_feature].loc[val_y.index])
             if self.stage1_metric == 'predictive':
                 params = {"n_estimators": 100, "importance_type": "gain", "num_leaves": 16,
-                          "seed": 1, "deterministic": True, "n_jobs": 1, "verbose": 1 if self.verbose else -1 }
+                          "seed": 1, "deterministic": True, "n_jobs": 1, "verbose": -1 }
                 if self.metric is not None:
                     params.update({"metric": self.metric})
                 if self.task == 'classification':
diff --git a/openfe/openfe.py b/openfe/openfe.py
index 8d7596c..3f670d8 100644
--- a/openfe/openfe.py
+++ b/openfe/openfe.py
@@ -406,7 +406,7 @@ def get_init_score(self, init_scores, use_train=False):
                 label = self.label.copy()
 
                 params = {"n_estimators": 10000, "learning_rate": 0.1, "metric": self.metric,
-                          "seed": self.seed, "n_jobs": self.n_jobs, "verbose": 1 if self.verbose else -1 }
+                          "seed": self.seed, "n_jobs": self.n_jobs, "verbose": -1}
                 if self.task == "regression":
                     gbm = lgb.LGBMRegressor(**params)
                 else:
@@ -536,7 +536,7 @@ def stage2_select(self):
         self.myprint("Finish data processing.")
         if self.stage2_params is None:
             params = {"n_estimators": 1000, "importance_type": "gain", "num_leaves": 16,
-                      "seed": 1, "n_jobs": self.n_jobs, "verbose": 1 if self.verbose else -1 }
+                      "seed": 1, "n_jobs": self.n_jobs, "verbose": -1 }
         else:
             params = self.stage2_params
         if self.metric is not None:
@@ -602,7 +602,7 @@ def _evaluate(self, candidate_feature, train_y, val_y, train_init, val_init, ini
             val_x = pd.DataFrame(candidate_feature.data.loc[val_y.index])
             if self.stage1_metric == 'predictive':
                 params = {"n_estimators": 100, "importance_type": "gain", "num_leaves": 16,
-                          "seed": 1, "deterministic": True, "n_jobs": 1, "verbose": 1 if self.verbose else -1 }
+                          "seed": 1, "deterministic": True, "n_jobs": 1, "verbose": -1}
                 if self.metric is not None:
                     params.update({"metric": self.metric})
                 if self.task == 'classification':
diff --git a/openfe/utils.py b/openfe/utils.py
index 306884e..81ed18f 100644
--- a/openfe/utils.py
+++ b/openfe/utils.py
@@ -1,9 +1,9 @@
 import traceback
 from .FeatureGenerator import Node, FNode
-from concurrent.futures import ProcessPoolExecutor
+from concurrent.futures import ProcessPoolExecutor, as_completed
 import pandas as pd
 import numpy as np
-
+from tqdm import tqdm
 
 def tree_to_formula(tree):
     if isinstance(tree, Node):
@@ -135,8 +135,13 @@ def transform(X_train, X_test, new_features_list, n_jobs, name=""):
     n_train = len(X_train)
     ex = ProcessPoolExecutor(n_jobs)
     results = []
-    for feature in new_features_list:
-        results.append(ex.submit(_cal, feature, n_train))
+    with tqdm(
+        total=len(new_features_list), desc="Calculating new features..."
+    ) as progress_bar:
+        results = [ex.submit(_cal, feature, n_train) for feature in new_features_list]
+        for feature in as_completed(results):
+            progress_bar.set_postfix(feature=feature.result()[-1])
+            progress_bar.update(1)
     ex.shutdown(wait=True)
     _train = []
     _test = []