diff --git a/HPC_setup/mlt_modules_juwels.sh b/HPC_setup/mlt_modules_juwels.sh
index 01eecbab617f7b3042222e24e562901b302d401e..8944b440143644984983a00ddda85a4a97b9db6d 100755
--- a/HPC_setup/mlt_modules_juwels.sh
+++ b/HPC_setup/mlt_modules_juwels.sh
@@ -8,14 +8,14 @@
 module --force purge
 module use $OTHERSTAGES
 
-ml Stages/2019a
-ml GCCcore/.8.3.0
+ml Stages/2020
+ml GCCcore/.9.3.0
 
-ml Jupyter/2019a-Python-3.6.8
-ml Python/3.6.8
-ml TensorFlow/1.13.1-GPU-Python-3.6.8
-ml Keras/2.2.4-GPU-Python-3.6.8
-ml SciPy-Stack/2019a-Python-3.6.8
-ml dask/1.1.5-Python-3.6.8
-ml GEOS/3.7.1-Python-3.6.8
-ml Graphviz/2.40.1
+ml Jupyter/2020.3.0-Python-3.8.5
+ml Python/3.8.5
+# ml TensorFlow/1.13.1-GPU-Python-3.6.8
+ml TensorFlow/2.3.1-Python-3.8.5
+ml SciPy-Stack/2020-Python-3.8.5
+ml dask/2.22.0-Python-3.8.5
+ml GEOS/3.8.1-Python-3.8.5
+ml Graphviz/2.44.1
diff --git a/mlair/run_modules/training.py b/mlair/run_modules/training.py
index cb538abbbcae2f1c4afdad70c8f621746fc26fbb..0696c2e7b8daa75925cf16096e183de94c21fe85 100644
--- a/mlair/run_modules/training.py
+++ b/mlair/run_modules/training.py
@@ -123,7 +123,7 @@ class Training(RunEnvironment):
 
     def train(self) -> None:
         """
-        Perform training using keras fit_generator().
+        Perform training using keras fit().
 
         Callbacks are stored locally in the experiment directory. Best model from training is saved for class
         variable model. If the file path of checkpoint is not empty, this method assumes, that this is not a new
@@ -261,7 +261,7 @@ class Training(RunEnvironment):
         tables.save_to_md(path, "training_settings.md", df=df)
 
         # calculate val scores
-        val_score = self.model.evaluate_generator(generator=self.val_set, use_multiprocessing=True, verbose=0)
+        val_score = self.model.evaluate(self.val_set, use_multiprocessing=True, verbose=0)
         path = self.data_store.get("model_path")
         with open(os.path.join(path, "val_scores.txt"), "a") as f:
             for index, item in enumerate(to_list(val_score)):