diff --git a/training/hyper/hyper_mp_perovskites.py b/training/hyper/hyper_mp_perovskites.py
index 4036ff16..a295cd90 100644
--- a/training/hyper/hyper_mp_perovskites.py
+++ b/training/hyper/hyper_mp_perovskites.py
@@ -79,13 +79,15 @@
             "config": {
                 "name": "PAiNN",
                 "inputs": [
-                    {"shape": [None], "name": "node_number", "dtype": "float32", "ragged": True},
+                    {"shape": [None], "name": "node_number", "dtype": "int64", "ragged": True},
                     {"shape": [None, 3], "name": "node_coordinates", "dtype": "float32", "ragged": True},
                     {"shape": [None, 2], "name": "range_indices", "dtype": "int64", "ragged": True},
                     {'shape': (None, 3), 'name': "range_image", 'dtype': 'int64', 'ragged': True},
                     {'shape': (3, 3), 'name': "graph_lattice", 'dtype': 'float32', 'ragged': False}
                 ],
-                "input_embedding": {"node": {"input_dim": 95, "output_dim": 128}},
+                "input_tensor_type": "ragged",
+                "input_embedding": None,
+                "input_node_embedding": {"input_dim": 95, "output_dim": 128},
                 "equiv_initialize_kwargs": {"dim": 3, "method": "eye"},
                 "bessel_basis": {"num_radial": 20, "cutoff": 5.0, "envelope_exponent": 5},
                 "pooling_args": {"pooling_method": "mean"},
@@ -109,11 +111,12 @@
                 ]
             },
             "compile": {
-                "optimizer": {"class_name": "Adam", "config": {"lr": 1e-04}},  # "clipnorm": 100.0, "clipvalue": 100.0}
+                "optimizer": {"class_name": "Adam", "config": {"learning_rate": 1e-04}},
+                # "clipnorm": 100.0, "clipvalue": 100.0}
                 "loss": "mean_absolute_error"
             },
             "scaler": {
-                "class_name": "StandardScaler",
+                "class_name": "StandardLabelScaler",
                 "module_name": "kgcnn.data.transform.scaler.standard",
                 "config": {"with_std": True, "with_mean": True, "copy": True}
             },
@@ -133,7 +136,300 @@
         "info": {
             "postfix": "",
             "postfix_file": "",
-            "kgcnn_version": "2.2.3"
+            "kgcnn_version": "4.0.0"
+        }
+    },
+    "Megnet.make_crystal_model": {
+        "model": {
+            "module_name": "kgcnn.literature.Megnet",
+            "class_name": "make_crystal_model",
+            "config": {
+                'name': "Megnet",
+                'inputs': [
+                    {'shape': (None,), 'name': "node_number", 'dtype': 'int64', 'ragged': True},
+                    {'shape': (None, 3), 'name': "node_coordinates", 'dtype': 'float32', 'ragged': True},
+                    {'shape': (None, 2), 'name': "range_indices", 'dtype': 'int64', 'ragged': True},
+                    {'shape': [1], 'name': "charge", 'dtype': 'float32', 'ragged': False},
+                    {'shape': (None, 3), 'name': "range_image", 'dtype': 'int64', 'ragged': True},
+                    {'shape': (3, 3), 'name': "graph_lattice", 'dtype': 'float32', 'ragged': False}
+                ],
+                "input_tensor_type": "ragged",
+                'input_embedding': None,
+                "input_node_embedding": {"input_dim": 95, "output_dim": 64},
+                # "input_edge_embedding": {"input_dim": 100, "output_dim": 64},
+                "make_distance": True, "expand_distance": True,
+                'gauss_args': {"bins": 25, "distance": 5, "offset": 0.0, "sigma": 0.4},
+                'meg_block_args': {'node_embed': [64, 32, 32], 'edge_embed': [64, 32, 32],
+                                   'env_embed': [64, 32, 32], 'activation': 'kgcnn>softplus2'},
+                'set2set_args': {'channels': 16, 'T': 3, "pooling_method": "sum", "init_qstar": "0"},
+                'node_ff_args': {"units": [64, 32], "activation": "kgcnn>softplus2"},
+                'edge_ff_args': {"units": [64, 32], "activation": "kgcnn>softplus2"},
+                'state_ff_args': {"units": [64, 32], "activation": "kgcnn>softplus2"},
+                'nblocks': 3, 'has_ff': True, 'dropout': None, 'use_set2set': True,
+                'verbose': 10,
+                'output_embedding': 'graph',
+                'output_mlp': {"use_bias": [True, True, True], "units": [32, 16, 1],
+                               "activation": ['kgcnn>softplus2', 'kgcnn>softplus2', 'linear']}
+            }
+        },
+        "training": {
+            "cross_validation": {"class_name": "KFold",
+                                 "config": {"n_splits": 5, "random_state": 42, "shuffle": True}},
+            "fit": {
+                "batch_size": 32, "epochs": 1000, "validation_freq": 10, "verbose": 2,
+                "callbacks": [
+                    {"class_name": "kgcnn>LinearLearningRateScheduler", "config": {
+                        "learning_rate_start": 0.0005, "learning_rate_stop": 0.5e-05, "epo_min": 100, "epo": 1000,
+                        "verbose": 0}
+                     }
+                ]
+            },
+            "compile": {
+                "optimizer": {"class_name": "Adam", "config": {"learning_rate": 0.0005}},
+                "loss": "mean_absolute_error"
+            },
+            "scaler": {
+                "class_name": "StandardLabelScaler",
+                "module_name": "kgcnn.data.transform.scaler.standard",
+                "config": {"with_std": True, "with_mean": True, "copy": True}
+            },
+            "multi_target_indices": None
+        },
+        "data": {
+            "dataset": {
+                "class_name": "MatProjectPerovskitesDataset",
+                "module_name": "kgcnn.data.datasets.MatProjectPerovskitesDataset",
+                "config": {},
+                "methods": [
+                    {"map_list": {"method": "set_range_periodic", "max_distance": 5.0}}
+                ]
+            },
+            "data_unit": "eV/unit_cell"
+        },
+        "info": {
+            "postfix": "",
+            "postfix_file": "",
+            "kgcnn_version": "4.0.0"
+        }
+    },
+    "DimeNetPP.make_crystal_model": {
+        "model": {
+            "class_name": "make_crystal_model",
+            "module_name": "kgcnn.literature.DimeNetPP",
+            "config": {
+                "name": "DimeNetPP",
+                "inputs": [{"shape": [None], "name": "node_number", "dtype": "int64", "ragged": True},
+                           {"shape": [None, 3], "name": "node_coordinates", "dtype": "float32", "ragged": True},
+                           {"shape": [None, 2], "name": "range_indices", "dtype": "int64", "ragged": True},
+                           {"shape": [None, 2], "name": "angle_indices", "dtype": "int64", "ragged": True},
+                           {'shape': (None, 3), 'name': "range_image", 'dtype': 'int64', 'ragged': True},
+                           {'shape': (3, 3), 'name': "graph_lattice", 'dtype': 'float32', 'ragged': False}
+                           ],
+                "input_tensor_type": "ragged",
+                "input_embedding": None,
+                "input_node_embedding": {"input_dim": 95, "output_dim": 128,
+                                         "embeddings_initializer": {"class_name": "RandomUniform",
+                                                                    "config": {"minval": -1.7320508075688772,
+                                                                               "maxval": 1.7320508075688772}}},
+                "emb_size": 128, "out_emb_size": 256, "int_emb_size": 64, "basis_emb_size": 8,
+                "num_blocks": 4, "num_spherical": 7, "num_radial": 6,
+                "cutoff": 5.0, "envelope_exponent": 5,
+                "num_before_skip": 1, "num_after_skip": 2, "num_dense_output": 3,
+                "num_targets": 1, "extensive": False, "output_init": "zeros",
+                "activation": "swish", "verbose": 10,
+                "output_embedding": "graph",
+                "use_output_mlp": False,
+                "output_mlp": {},
+            }
+        },
+        "training": {
+            "cross_validation": {"class_name": "KFold",
+                                 "config": {"n_splits": 5, "random_state": 42, "shuffle": True}},
+            "fit": {
+                "batch_size": 16, "epochs": 780, "validation_freq": 10, "verbose": 2, "callbacks": [],
+                "validation_batch_size": 8
+            },
+            "compile": {
+                "optimizer": {
+                    "class_name": "Adam",
+                    "config": {
+                        "learning_rate": {
+                            "class_name": "kgcnn>LinearWarmupExponentialDecay", "config": {
+                                "learning_rate": 0.001, "warmup_steps": 3000.0, "decay_steps": 4000000.0,
+                                "decay_rate": 0.01
+                            }
+                        },
+                        "use_ema": True,
+                        "amsgrad": True,
+                    }
+                },
+                "loss": "mean_absolute_error"
+            },
+            "scaler": {
+                "class_name": "StandardLabelScaler",
+                "module_name": "kgcnn.data.transform.scaler.standard",
+                "config": {"with_std": True, "with_mean": True, "copy": True}
+            },
+            "multi_target_indices": None
+        },
+        "data": {
+            "dataset": {
+                "class_name": "MatProjectPerovskitesDataset",
+                "module_name": "kgcnn.data.datasets.MatProjectPerovskitesDataset",
+                "config": {},
+                "methods": [
+                    {"map_list": {"method": "set_range_periodic", "max_distance": 5.0, "max_neighbours": 17}},
+                    {"map_list": {"method": "set_angle", "allow_multi_edges": True, "allow_reverse_edges": True}}
+                ]
+            },
+        },
+        "info": {
+            "postfix": "",
+            "postfix_file": "",
+            "kgcnn_version": "4.0.0"
+        }
+    },
+    "CGCNN.make_crystal_model": {
+        "model": {
+            "class_name": "make_crystal_model",
+            "module_name": "kgcnn.literature.CGCNN",
+            "config": {
+                'name': 'CGCNN',
+                'inputs': [
+                    {'shape': (None,), 'name': 'node_number', 'dtype': 'int64', 'ragged': True},
+                    {'shape': (None, 3), 'name': 'node_frac_coordinates', 'dtype': 'float64', 'ragged': True},
+                    {'shape': (None, 2), 'name': 'range_indices', 'dtype': 'int64', 'ragged': True},
+                    {'shape': (3, 3), 'name': 'graph_lattice', 'dtype': 'float64', 'ragged': False},
+                    {'shape': (None, 3), 'name': 'range_image', 'dtype': 'float32', 'ragged': True},
+                    # For `representation="asu"`:
+                    # {'shape': (None, 1), 'name': 'multiplicities', 'dtype': 'float32', 'ragged': True},
+                    # {'shape': (None, 4, 4), 'name': 'symmops', 'dtype': 'float64', 'ragged': True},
+                ],
+                "input_tensor_type": "ragged",
+                'input_node_embedding': {'input_dim': 95, 'output_dim': 64},
+                'representation': 'unit',  # None, 'asu' or 'unit'
+                'expand_distance': True,
+                'make_distances': True,
+                'gauss_args': {'bins': 60, 'distance': 6, 'offset': 0.0, 'sigma': 0.4},
+                'conv_layer_args': {
+                    'units': 128,
+                    'activation_s': 'kgcnn>shifted_softplus',
+                    'activation_out': 'kgcnn>shifted_softplus',
+                    'batch_normalization': True,
+                },
+                'node_pooling_args': {'pooling_method': 'mean'},
+                'depth': 4,
+                'output_mlp': {'use_bias': [True, True, False], 'units': [128, 64, 1],
+                               'activation': ['kgcnn>shifted_softplus', 'kgcnn>shifted_softplus', 'linear']},
+            }
+        },
+        "training": {
+            "cross_validation": {"class_name": "KFold",
+                                 "config": {"n_splits": 5, "random_state": 42, "shuffle": True}},
+            "fit": {
+                "batch_size": 128, "epochs": 1000, "validation_freq": 10, "verbose": 2,
+                "callbacks": [
+                    {"class_name": "kgcnn>LinearLearningRateScheduler", "config": {
+                        "learning_rate_start": 1e-03, "learning_rate_stop": 1e-05, "epo_min": 500, "epo": 1000,
+                        "verbose": 0}
+                     }
+                ]
+            },
+            "compile": {
+                "optimizer": {"class_name": "Adam", "config": {"learning_rate": 1e-03}},
+                "loss": "mean_absolute_error"
+            },
+            "scaler": {
+                "class_name": "StandardLabelScaler",
+                "module_name": "kgcnn.data.transform.scaler.standard",
+                "config": {"with_std": True, "with_mean": True, "copy": True}
+            },
+            "multi_target_indices": None
+        },
+        "data": {
+            "dataset": {
+                "class_name": "MatProjectPerovskitesDataset",
+                "module_name": "kgcnn.data.datasets.MatProjectPerovskitesDataset",
+                "config": {},
+                "methods": [
+                    {"map_list": {"method": "set_range_periodic", "max_distance": 6.0}}
+                ]
+            },
+            "data_unit": "eV/unit_cell"
+        },
+        "info": {
+            "postfix": "",
+            "postfix_file": "",
+            "kgcnn_version": "4.0.0"
+        }
+    },
+    "NMPN.make_crystal_model": {
+        "model": {
+            "class_name": "make_crystal_model",
+            "module_name": "kgcnn.literature.NMPN",
+            "config": {
+                "name": "NMPN",
+                "inputs": [
+                    {"shape": [None], "name": "node_number", "dtype": "int64", "ragged": True},
+                    {"shape": [None, 3], "name": "node_coordinates", "dtype": "float32", "ragged": True},
+                    {"shape": [None, 2], "name": "range_indices", "dtype": "int64", "ragged": True},
+                    {'shape': (None, 3), 'name': "range_image", 'dtype': 'int64', 'ragged': True},
+                    {'shape': (3, 3), 'name': "graph_lattice", 'dtype': 'float32', 'ragged': False}
+                ],
+                "input_tensor_type": "ragged",
+                "input_embedding": None,
+                "input_node_embedding": {"input_dim": 95, "output_dim": 64},
+                "input_edge_embedding": {"input_dim": 5, "output_dim": 64},
+                "set2set_args": {"channels": 32, "T": 3, "pooling_method": "sum", "init_qstar": "0"},
+                "pooling_args": {"pooling_method": "segment_mean"},
+                "use_set2set": True,
+                "depth": 3,
+                "node_dim": 128,
+                "verbose": 10,
+                "geometric_edge": True, "make_distance": True, "expand_distance": True,
+                "output_embedding": "graph",
+                "output_mlp": {"use_bias": [True, True, False], "units": [25, 25, 1],
+                               "activation": ["selu", "selu", "linear"]},
+            }
+        },
+        "training": {
+            "cross_validation": {"class_name": "KFold",
+                                 "config": {"n_splits": 5, "random_state": 42, "shuffle": True}},
+            "fit": {
+                "batch_size": 16, "epochs": 700, "validation_freq": 10, "verbose": 2,
+                "callbacks": [
+                    {"class_name": "kgcnn>LinearLearningRateScheduler", "config": {
+                        "learning_rate_start": 1e-04, "learning_rate_stop": 1e-05, "epo_min": 50, "epo": 700,
+                        "verbose": 0
+                    }
+                     }
+                ]
+            },
+            "compile": {
+                "optimizer": {"class_name": "Adam", "config": {"learning_rate": 1e-04}},
+                "loss": "mean_absolute_error"
+            },
+            "scaler": {
+                "class_name": "StandardLabelScaler",
+                "module_name": "kgcnn.data.transform.scaler.standard",
+                "config": {"with_std": True, "with_mean": True, "copy": True}
+            },
+            "multi_target_indices": None
+        },
+        "data": {
+            "dataset": {
+                "class_name": "MatProjectPerovskitesDataset",
+                "module_name": "kgcnn.data.datasets.MatProjectPerovskitesDataset",
+                "config": {},
+                "methods": [
+                    {"map_list": {"method": "set_range_periodic", "max_distance": 5.0}}
+                ]
+            },
+        },
+        "info": {
+            "postfix": "",
+            "postfix_file": "",
+            "kgcnn_version": "4.0.0"
         }
     },
 }
diff --git a/training/hyper/hyper_qm9_energies.py b/training/hyper/hyper_qm9_energies.py
index 67b11dca..4482a837 100644
--- a/training/hyper/hyper_qm9_energies.py
+++ b/training/hyper/hyper_qm9_energies.py
@@ -231,10 +231,13 @@
                 ],
                 "input_tensor_type": "ragged",
                 "input_embedding": None,
+                "equiv_initialize_kwargs": {"dim": 3, "method": "eps", "units": 128},
                 "input_node_embedding": {"input_dim": 95, "output_dim": 128},
                 "bessel_basis": {"num_radial": 20, "cutoff": 5.0, "envelope_exponent": 5},
-                "pooling_args": {"pooling_method": "sum"}, "conv_args": {"units": 128, "cutoff": None},
-                "update_args": {"units": 128}, "depth": 3, "verbose": 10,
+                "pooling_args": {"pooling_method": "sum"},
+                "conv_args": {"units": 128, "cutoff": None},
+                "update_args": {"units": 128, "add_eps": True},
+                "depth": 3, "verbose": 10,
                 "output_embedding": "graph",
                 "output_mlp": {"use_bias": [True, True], "units": [128, 1], "activation": ["swish", "linear"]},
             }
diff --git a/training/results/MatProjectDielectricDataset/CGCNN_make_crystal_model/CGCNN_MatProjectDielectricDataset_score.yaml b/training/results/MatProjectDielectricDataset/CGCNN_make_crystal_model/CGCNN_MatProjectDielectricDataset_score.yaml
new file mode 100644
index 00000000..8ab5c1eb
--- /dev/null
+++ b/training/results/MatProjectDielectricDataset/CGCNN_make_crystal_model/CGCNN_MatProjectDielectricDataset_score.yaml
@@ -0,0 +1,156 @@
+OS: posix_linux
+backend: tensorflow
+cuda_available: 'True'
+data_unit: ''
+date_time: '2023-12-22 12:27:35'
+device_id: '[LogicalDevice(name=''/device:CPU:0'', device_type=''CPU''), LogicalDevice(name=''/device:GPU:0'',
+  device_type=''GPU'')]'
+device_memory: '[]'
+device_name: '[{}, {''compute_capability'': (8, 0), ''device_name'': ''NVIDIA A100
+  80GB PCIe''}]'
+epochs:
+- 1000
+- 1000
+- 1000
+- 1000
+- 1000
+execute_folds: null
+kgcnn_version: 4.0.0
+learning_rate:
+- 1.1979999726463575e-05
+- 1.1979999726463575e-05
+- 1.1979999726463575e-05
+- 1.1979999726463575e-05
+- 1.1979999726463575e-05
+loss:
+- 0.003908407408744097
+- 0.004692154470831156
+- 0.006342913489788771
+- 0.0035230836365371943
+- 0.009283904917538166
+max_learning_rate:
+- 0.0010000000474974513
+- 0.0010000000474974513
+- 0.0010000000474974513
+- 0.0010000000474974513
+- 0.0010000000474974513
+max_loss:
+- 0.29928597807884216
+- 0.2982141375541687
+- 0.34784677624702454
+- 0.33266669511795044
+- 0.2964531183242798
+max_scaled_mean_absolute_error:
+- 0.6703238487243652
+- 0.6486446857452393
+- 0.6615451574325562
+- 0.6476733088493347
+- 0.6645464301109314
+max_scaled_root_mean_squared_error:
+- 2.226531505584717
+- 2.1471033096313477
+- 1.961928367614746
+- 1.9316452741622925
+- 2.2292592525482178
+max_val_loss:
+- 0.13875462114810944
+- 0.17157776653766632
+- 0.2204970121383667
+- 0.241636723279953
+- 0.15825790166854858
+max_val_scaled_mean_absolute_error:
+- 0.30842339992523193
+- 0.37336939573287964
+- 0.43662363290786743
+- 0.47117704153060913
+- 0.36141663789749146
+max_val_scaled_root_mean_squared_error:
+- 1.2602670192718506
+- 1.8693556785583496
+- 3.8716259002685547
+- 2.9088242053985596
+- 2.1601967811584473
+min_learning_rate:
+- 1.1979999726463575e-05
+- 1.1979999726463575e-05
+- 1.1979999726463575e-05
+- 1.1979999726463575e-05
+- 1.1979999726463575e-05
+min_loss:
+- 0.00390807818621397
+- 0.004692154470831156
+- 0.006342913489788771
+- 0.0035230836365371943
+- 0.009283904917538166
+min_scaled_mean_absolute_error:
+- 0.008782914839684963
+- 0.010183566249907017
+- 0.012111489661037922
+- 0.006886749062687159
+- 0.02086334303021431
+min_scaled_root_mean_squared_error:
+- 0.13632167875766754
+- 0.12522505223751068
+- 0.190583735704422
+- 0.07955355197191238
+- 0.5195185542106628
+min_val_loss:
+- 0.10097754001617432
+- 0.1282927393913269
+- 0.1741935908794403
+- 0.18756960332393646
+- 0.12386748194694519
+min_val_scaled_mean_absolute_error:
+- 0.2205708771944046
+- 0.2831050455570221
+- 0.3451306223869324
+- 0.38085973262786865
+- 0.2762523591518402
+min_val_scaled_root_mean_squared_error:
+- 1.1485005617141724
+- 1.4987907409667969
+- 2.642016649246216
+- 2.443527936935425
+- 1.123365879058838
+model_class: make_crystal_model
+model_name: CGCNN
+model_version: '2023-11-28'
+multi_target_indices: null
+number_histories: 5
+scaled_mean_absolute_error:
+- 0.00878499262034893
+- 0.010183566249907017
+- 0.012111489661037922
+- 0.006886749062687159
+- 0.02086334303021431
+scaled_root_mean_squared_error:
+- 0.13636255264282227
+- 0.12528164684772491
+- 0.19060498476028442
+- 0.07955954968929291
+- 0.5195185542106628
+seed: 42
+time_list:
+- '0:24:17.400906'
+- '0:24:19.909013'
+- '0:24:28.518577'
+- '0:24:28.251962'
+- '0:24:04.352241'
+val_loss:
+- 0.11400707066059113
+- 0.14116309583187103
+- 0.19164298474788666
+- 0.20423556864261627
+- 0.13235312700271606
+val_scaled_mean_absolute_error:
+- 0.2466062605381012
+- 0.3129154443740845
+- 0.3801003396511078
+- 0.4156058132648468
+- 0.29770055413246155
+val_scaled_root_mean_squared_error:
+- 1.2402254343032837
+- 1.694710373878479
+- 3.0533506870269775
+- 2.6101980209350586
+- 1.2695704698562622
diff --git a/training/results/MatProjectDielectricDataset/CGCNN_make_crystal_model/CGCNN_hyper.json b/training/results/MatProjectDielectricDataset/CGCNN_make_crystal_model/CGCNN_hyper.json
new file mode 100644
index 00000000..0df0d93a
--- /dev/null
+++ b/training/results/MatProjectDielectricDataset/CGCNN_make_crystal_model/CGCNN_hyper.json
@@ -0,0 +1 @@
+{"model": {"class_name": "make_crystal_model", "module_name": "kgcnn.literature.CGCNN", "config": {"name": "CGCNN", "inputs": [{"shape": [null], "name": "node_number", "dtype": "int64", "ragged": true}, {"shape": [null, 3], "name": "node_frac_coordinates", "dtype": "float64", "ragged": true}, {"shape": [null, 2], "name": "range_indices", "dtype": "int64", "ragged": true}, {"shape": [null, 3], "name": "range_image", "dtype": "float32", "ragged": true}, {"shape": [3, 3], "name": "graph_lattice", "dtype": "float64", "ragged": false}], "input_tensor_type": "ragged", "input_node_embedding": {"input_dim": 95, "output_dim": 64}, "representation": "unit", "expand_distance": true, "make_distances": true, "gauss_args": {"bins": 60, "distance": 6, "offset": 0.0, "sigma": 0.4}, "conv_layer_args": {"units": 128, "activation_s": "kgcnn>shifted_softplus", "activation_out": "kgcnn>shifted_softplus", "batch_normalization": true}, "node_pooling_args": {"pooling_method": "mean"}, "depth": 4, "output_mlp": {"use_bias": [true, true, false], "units": [128, 64, 1], "activation": ["kgcnn>shifted_softplus", "kgcnn>shifted_softplus", "linear"]}}}, "training": {"cross_validation": {"class_name": "KFold", "config": {"n_splits": 5, "random_state": 42, "shuffle": true}}, "fit": {"batch_size": 128, "epochs": 1000, "validation_freq": 10, "verbose": 2, "callbacks": [{"class_name": "kgcnn>LinearLearningRateScheduler", "config": {"learning_rate_start": 0.001, "learning_rate_stop": 1e-05, "epo_min": 500, "epo": 1000, "verbose": 0}}]}, "compile": {"optimizer": {"class_name": "Adam", "config": {"learning_rate": 0.001}}, "loss": "mean_absolute_error"}, "scaler": {"class_name": "StandardLabelScaler", "module_name": "kgcnn.data.transform.scaler.standard", "config": {"with_std": true, "with_mean": true, "copy": true}}, "multi_target_indices": null}, "data": {"data_unit": ""}, "info": {"postfix": "", "postfix_file": "", "kgcnn_version": "4.0.0"}, "dataset": {"class_name": "MatProjectDielectricDataset", "module_name": "kgcnn.data.datasets.MatProjectDielectricDataset", "config": {}, "methods": [{"map_list": {"method": "set_range_periodic", "max_distance": 6.0}}]}}
\ No newline at end of file
diff --git a/training/results/MatProjectDielectricDataset/DimeNetPP_make_crystal_model/DimeNetPP_MatProjectDielectricDataset_score.yaml b/training/results/MatProjectDielectricDataset/DimeNetPP_make_crystal_model/DimeNetPP_MatProjectDielectricDataset_score.yaml
new file mode 100644
index 00000000..57a7c2c6
--- /dev/null
+++ b/training/results/MatProjectDielectricDataset/DimeNetPP_make_crystal_model/DimeNetPP_MatProjectDielectricDataset_score.yaml
@@ -0,0 +1,138 @@
+OS: posix_linux
+backend: tensorflow
+cuda_available: 'True'
+data_unit: ''
+date_time: '2023-12-23 08:04:54'
+device_id: '[LogicalDevice(name=''/device:CPU:0'', device_type=''CPU''), LogicalDevice(name=''/device:GPU:0'',
+  device_type=''GPU'')]'
+device_memory: '[]'
+device_name: '[{}, {''compute_capability'': (8, 0), ''device_name'': ''NVIDIA A100
+  80GB PCIe''}]'
+epochs:
+- 780
+- 780
+- 780
+- 780
+- 780
+execute_folds: null
+kgcnn_version: 4.0.0
+loss:
+- 0.014057300053536892
+- 0.010803972370922565
+- 0.021847454831004143
+- 0.010845025070011616
+- 0.011277178302407265
+max_loss:
+- 0.2894236743450165
+- 0.2874397933483124
+- 0.3249437212944031
+- 0.3085272014141083
+- 0.27760064601898193
+max_scaled_mean_absolute_error:
+- 0.6463800668716431
+- 0.6232023239135742
+- 0.6177472472190857
+- 0.6019346714019775
+- 0.6214737892150879
+max_scaled_root_mean_squared_error:
+- 6.353706359863281
+- 3.6533138751983643
+- 1.958578109741211
+- 1.9420709609985352
+- 2.1996052265167236
+max_val_loss:
+- 0.13525769114494324
+- 0.17753571271896362
+- 0.2074926197528839
+- 0.22895796597003937
+- 0.17164599895477295
+max_val_scaled_mean_absolute_error:
+- 0.30287641286849976
+- 0.3873569369316101
+- 0.3958742022514343
+- 0.4489605128765106
+- 0.383497416973114
+max_val_scaled_root_mean_squared_error:
+- 1.3586090803146362
+- 2.2312710285186768
+- 2.859815835952759
+- 2.7745842933654785
+- 1.3450583219528198
+min_loss:
+- 0.01219440158456564
+- 0.009662896394729614
+- 0.018989339470863342
+- 0.009106690995395184
+- 0.010300984606146812
+min_scaled_mean_absolute_error:
+- 0.027299804612994194
+- 0.02097909525036812
+- 0.036130934953689575
+- 0.01777823083102703
+- 0.023068921640515327
+min_scaled_root_mean_squared_error:
+- 0.2014225572347641
+- 0.10508611798286438
+- 0.501449465751648
+- 0.0927872508764267
+- 0.11724021285772324
+min_val_loss:
+- 0.10301823168992996
+- 0.13266600668430328
+- 0.17175425589084625
+- 0.19746853411197662
+- 0.12582111358642578
+min_val_scaled_mean_absolute_error:
+- 0.22966936230659485
+- 0.2892354428768158
+- 0.3282586932182312
+- 0.3874290883541107
+- 0.28111377358436584
+min_val_scaled_root_mean_squared_error:
+- 1.1320940256118774
+- 1.506567358970642
+- 2.6247448921203613
+- 2.4886317253112793
+- 1.1282464265823364
+model_class: make_crystal_model
+model_name: DimeNetPP
+model_version: '2023-12-04'
+multi_target_indices: null
+number_histories: 5
+scaled_mean_absolute_error:
+- 0.031458765268325806
+- 0.023461701348423958
+- 0.041570551693439484
+- 0.02117619290947914
+- 0.025246215984225273
+scaled_root_mean_squared_error:
+- 0.4024450182914734
+- 0.18166032433509827
+- 0.6014757752418518
+- 0.15766005218029022
+- 0.2094792276620865
+seed: 42
+time_list:
+- '2:38:15.313714'
+- '2:37:50.756940'
+- '2:39:02.301760'
+- '2:36:29.045249'
+- '2:37:01.667458'
+val_loss:
+- 0.11314921826124191
+- 0.17160314321517944
+- 0.18356828391551971
+- 0.21024750173091888
+- 0.14224718511104584
+val_scaled_mean_absolute_error:
+- 0.2523866891860962
+- 0.3744055926799774
+- 0.35041993856430054
+- 0.41256359219551086
+- 0.3178134560585022
+val_scaled_root_mean_squared_error:
+- 1.1950279474258423
+- 2.0859673023223877
+- 2.711789846420288
+- 2.556424617767334
+- 1.2692707777023315
diff --git a/training/results/MatProjectDielectricDataset/DimeNetPP_make_crystal_model/DimeNetPP_hyper.json b/training/results/MatProjectDielectricDataset/DimeNetPP_make_crystal_model/DimeNetPP_hyper.json
new file mode 100644
index 00000000..d1163bce
--- /dev/null
+++ b/training/results/MatProjectDielectricDataset/DimeNetPP_make_crystal_model/DimeNetPP_hyper.json
@@ -0,0 +1 @@
+{"model": {"class_name": "make_crystal_model", "module_name": "kgcnn.literature.DimeNetPP", "config": {"name": "DimeNetPP", "inputs": [{"shape": [null], "name": "node_number", "dtype": "int64", "ragged": true}, {"shape": [null, 3], "name": "node_coordinates", "dtype": "float32", "ragged": true}, {"shape": [null, 2], "name": "range_indices", "dtype": "int64", "ragged": true}, {"shape": [null, 2], "name": "angle_indices", "dtype": "int64", "ragged": true}, {"shape": [null, 3], "name": "range_image", "dtype": "int64", "ragged": true}, {"shape": [3, 3], "name": "graph_lattice", "dtype": "float32", "ragged": false}], "input_tensor_type": "ragged", "input_embedding": null, "input_node_embedding": {"input_dim": 95, "output_dim": 128, "embeddings_initializer": {"class_name": "RandomUniform", "config": {"minval": -1.7320508075688772, "maxval": 1.7320508075688772}}}, "emb_size": 128, "out_emb_size": 256, "int_emb_size": 64, "basis_emb_size": 8, "num_blocks": 4, "num_spherical": 7, "num_radial": 6, "cutoff": 5.0, "envelope_exponent": 5, "num_before_skip": 1, "num_after_skip": 2, "num_dense_output": 3, "num_targets": 1, "extensive": false, "output_init": "zeros", "activation": "swish", "verbose": 10, "output_embedding": "graph", "use_output_mlp": false, "output_mlp": {}}}, "training": {"cross_validation": {"class_name": "KFold", "config": {"n_splits": 5, "random_state": 42, "shuffle": true}}, "fit": {"batch_size": 16, "epochs": 780, "validation_freq": 10, "verbose": 2, "callbacks": [], "validation_batch_size": 8}, "compile": {"optimizer": {"class_name": "Adam", "config": {"learning_rate": {"class_name": "kgcnn>LinearWarmupExponentialDecay", "config": {"learning_rate": 0.001, "warmup_steps": 3000.0, "decay_steps": 4000000.0, "decay_rate": 0.01}}, "use_ema": true, "amsgrad": true}}, "loss": "mean_absolute_error"}, "scaler": {"class_name": "StandardLabelScaler", "module_name": "kgcnn.data.transform.scaler.standard", "config": {"with_std": true, "with_mean": true, "copy": true}}, "multi_target_indices": null}, "data": {}, "info": {"postfix": "", "postfix_file": "", "kgcnn_version": "4.0.0"}, "dataset": {"class_name": "MatProjectDielectricDataset", "module_name": "kgcnn.data.datasets.MatProjectDielectricDataset", "config": {}, "methods": [{"map_list": {"method": "set_range_periodic", "max_distance": 5.0, "max_neighbours": 17}}, {"map_list": {"method": "set_angle", "allow_multi_edges": true, "allow_reverse_edges": true}}]}}
\ No newline at end of file
diff --git a/training/results/MatProjectDielectricDataset/Megnet_make_crystal_model/Megnet_MatProjectDielectricDataset_score.yaml b/training/results/MatProjectDielectricDataset/Megnet_make_crystal_model/Megnet_MatProjectDielectricDataset_score.yaml
new file mode 100644
index 00000000..f178d7e0
--- /dev/null
+++ b/training/results/MatProjectDielectricDataset/Megnet_make_crystal_model/Megnet_MatProjectDielectricDataset_score.yaml
@@ -0,0 +1,156 @@
+OS: posix_linux
+backend: tensorflow
+cuda_available: 'True'
+data_unit: ''
+date_time: '2023-12-22 18:53:07'
+device_id: '[LogicalDevice(name=''/device:CPU:0'', device_type=''CPU''), LogicalDevice(name=''/device:GPU:0'',
+  device_type=''GPU'')]'
+device_memory: '[]'
+device_name: '[{}, {''compute_capability'': (8, 0), ''device_name'': ''NVIDIA A100
+  80GB PCIe''}]'
+epochs:
+- 1000
+- 1000
+- 1000
+- 1000
+- 1000
+execute_folds: null
+kgcnn_version: 4.0.0
+learning_rate:
+- 5.549999968934571e-06
+- 5.549999968934571e-06
+- 5.549999968934571e-06
+- 5.549999968934571e-06
+- 5.549999968934571e-06
+loss:
+- 0.014145629480481148
+- 0.015394561924040318
+- 0.010281166061758995
+- 0.020196018740534782
+- 0.0135773541405797
+max_learning_rate:
+- 0.0005000000237487257
+- 0.0005000000237487257
+- 0.0005000000237487257
+- 0.0005000000237487257
+- 0.0005000000237487257
+max_loss:
+- 0.2674420475959778
+- 0.2643362879753113
+- 0.296357125043869
+- 0.27882102131843567
+- 0.25964516401290894
+max_scaled_mean_absolute_error:
+- 0.5965599417686462
+- 0.575202465057373
+- 0.5644909143447876
+- 0.5465184450149536
+- 0.5821710824966431
+max_scaled_root_mean_squared_error:
+- 2.1822314262390137
+- 2.120189666748047
+- 1.8238959312438965
+- 1.8660461902618408
+- 2.1841845512390137
+max_val_loss:
+- 0.13648812472820282
+- 0.17681798338890076
+- 0.2001328021287918
+- 0.24460354447364807
+- 0.15875595808029175
+max_val_scaled_mean_absolute_error:
+- 0.30587321519851685
+- 0.38238096237182617
+- 0.38088738918304443
+- 0.4783532917499542
+- 0.35493728518486023
+max_val_scaled_root_mean_squared_error:
+- 1.2681126594543457
+- 2.1423847675323486
+- 2.9369139671325684
+- 2.814467430114746
+- 2.0597116947174072
+min_learning_rate:
+- 5.549999968934571e-06
+- 5.549999968934571e-06
+- 5.549999968934571e-06
+- 5.549999968934571e-06
+- 5.549999968934571e-06
+min_loss:
+- 0.014145629480481148
+- 0.015317759476602077
+- 0.01019623875617981
+- 0.020196018740534782
+- 0.01353900134563446
+min_scaled_mean_absolute_error:
+- 0.031855881214141846
+- 0.03343827277421951
+- 0.019463298842310905
+- 0.03963746875524521
+- 0.030455434694886208
+min_scaled_root_mean_squared_error:
+- 0.8225930333137512
+- 0.5400567054748535
+- 0.17158764600753784
+- 0.9325186014175415
+- 0.8516271114349365
+min_val_loss:
+- 0.10235300660133362
+- 0.12791842222213745
+- 0.17398902773857117
+- 0.2005777657032013
+- 0.12160424143075943
+min_val_scaled_mean_absolute_error:
+- 0.22949418425559998
+- 0.2769976258277893
+- 0.331879198551178
+- 0.39263901114463806
+- 0.272493451833725
+min_val_scaled_root_mean_squared_error:
+- 1.1132538318634033
+- 1.5458210706710815
+- 2.642765998840332
+- 2.3388073444366455
+- 1.067321538925171
+model_class: make_crystal_model
+model_name: Megnet
+model_version: '2023-12-05'
+multi_target_indices: null
+number_histories: 5
+scaled_mean_absolute_error:
+- 0.031855881214141846
+- 0.03360515832901001
+- 0.01962600275874138
+- 0.03963746875524521
+- 0.03054564632475376
+scaled_root_mean_squared_error:
+- 0.8225930333137512
+- 0.5401650667190552
+- 0.17158764600753784
+- 0.9325875639915466
+- 0.8516433238983154
+seed: 42
+time_list:
+- '1:16:59.594989'
+- '1:15:57.563823'
+- '1:16:13.330252'
+- '1:16:19.255688'
+- '1:16:16.148780'
+val_loss:
+- 0.10464973002672195
+- 0.15489736199378967
+- 0.19287802278995514
+- 0.20286598801612854
+- 0.1547670066356659
+val_scaled_mean_absolute_error:
+- 0.23449218273162842
+- 0.3356344401836395
+- 0.3680046498775482
+- 0.39704418182373047
+- 0.345729261636734
+val_scaled_root_mean_squared_error:
+- 1.1261394023895264
+- 1.98274564743042
+- 2.8357961177825928
+- 2.422797441482544
+- 1.7104519605636597
diff --git a/training/results/MatProjectDielectricDataset/Megnet_make_crystal_model/Megnet_hyper.json b/training/results/MatProjectDielectricDataset/Megnet_make_crystal_model/Megnet_hyper.json
new file mode 100644
index 00000000..485971e7
--- /dev/null
+++ b/training/results/MatProjectDielectricDataset/Megnet_make_crystal_model/Megnet_hyper.json
@@ -0,0 +1 @@
+{"model": {"module_name": "kgcnn.literature.Megnet", "class_name": "make_crystal_model", "config": {"name": "Megnet", "inputs": [{"shape": [null], "name": "node_number", "dtype": "int64", "ragged": true}, {"shape": [null, 3], "name": "node_coordinates", "dtype": "float32", "ragged": true}, {"shape": [null, 2], "name": "range_indices", "dtype": "int64", "ragged": true}, {"shape": [1], "name": "charge", "dtype": "float32", "ragged": false}, {"shape": [null, 3], "name": "range_image", "dtype": "int64", "ragged": true}, {"shape": [3, 3], "name": "graph_lattice", "dtype": "float32", "ragged": false}], "input_tensor_type": "ragged", "input_embedding": null, "input_node_embedding": {"input_dim": 95, "output_dim": 64}, "make_distance": true, "expand_distance": true, "gauss_args": {"bins": 25, "distance": 5, "offset": 0.0, "sigma": 0.4}, "meg_block_args": {"node_embed": [64, 32, 32], "edge_embed": [64, 32, 32], "env_embed": [64, 32, 32], "activation": "kgcnn>softplus2"}, "set2set_args": {"channels": 16, "T": 3, "pooling_method": "sum", "init_qstar": "0"}, "node_ff_args": {"units": [64, 32], "activation": "kgcnn>softplus2"}, "edge_ff_args": {"units": [64, 32], "activation": "kgcnn>softplus2"}, "state_ff_args": {"units": [64, 32], "activation": "kgcnn>softplus2"}, "nblocks": 3, "has_ff": true, "dropout": null, "use_set2set": true, "verbose": 10, "output_embedding": "graph", "output_mlp": {"use_bias": [true, true, true], "units": [32, 16, 1], "activation": ["kgcnn>softplus2", "kgcnn>softplus2", "linear"]}}}, "training": {"cross_validation": {"class_name": "KFold", "config": {"n_splits": 5, "random_state": 42, "shuffle": true}}, "fit": {"batch_size": 32, "epochs": 1000, "validation_freq": 10, "verbose": 2, "callbacks": [{"class_name": "kgcnn>LinearLearningRateScheduler", "config": {"learning_rate_start": 0.0005, "learning_rate_stop": 5e-06, "epo_min": 100, "epo": 1000, "verbose": 0}}]}, "compile": {"optimizer": {"class_name": "Adam", "config": {"learning_rate": 0.0005}}, "loss": "mean_absolute_error"}, "scaler": {"class_name": "StandardLabelScaler", "module_name": "kgcnn.data.transform.scaler.standard", "config": {"with_std": true, "with_mean": true, "copy": true}}, "multi_target_indices": null}, "data": {"data_unit": ""}, "info": {"postfix": "", "postfix_file": "", "kgcnn_version": "4.0.0"}, "dataset": {"class_name": "MatProjectDielectricDataset", "module_name": "kgcnn.data.datasets.MatProjectDielectricDataset", "config": {}, "methods": [{"map_list": {"method": "set_range_periodic", "max_distance": 5.0}}]}}
\ No newline at end of file
diff --git a/training/results/MatProjectDielectricDataset/NMPN_make_crystal_model/NMPN_MatProjectDielectricDataset_score.yaml b/training/results/MatProjectDielectricDataset/NMPN_make_crystal_model/NMPN_MatProjectDielectricDataset_score.yaml
new file mode 100644
index 00000000..9510c68f
--- /dev/null
+++ b/training/results/MatProjectDielectricDataset/NMPN_make_crystal_model/NMPN_MatProjectDielectricDataset_score.yaml
@@ -0,0 +1,156 @@
+OS: posix_linux
+backend: tensorflow
+cuda_available: 'True'
+data_unit: ''
+date_time: '2023-12-23 21:32:09'
+device_id: '[LogicalDevice(name=''/device:CPU:0'', device_type=''CPU''), LogicalDevice(name=''/device:GPU:0'',
+  device_type=''GPU'')]'
+device_memory: '[]'
+device_name: '[{}, {''compute_capability'': (8, 0), ''device_name'': ''NVIDIA A100
+  80GB PCIe''}]'
+epochs:
+- 700
+- 700
+- 700
+- 700
+- 700
+execute_folds: null
+kgcnn_version: 4.0.0
+learning_rate:
+- 1.0138461220776662e-05
+- 1.0138461220776662e-05
+- 1.0138461220776662e-05
+- 1.0138461220776662e-05
+- 1.0138461220776662e-05
+loss:
+- 0.024377649649977684
+- 0.01715400442481041
+- 0.023170247673988342
+- 0.02199258841574192
+- 0.015595770440995693
+max_learning_rate:
+- 9.999999747378752e-05
+- 9.999999747378752e-05
+- 9.999999747378752e-05
+- 9.999999747378752e-05
+- 9.999999747378752e-05
+max_loss:
+- 0.24615450203418732
+- 0.2426282912492752
+- 0.27957653999328613
+- 0.260698527097702
+- 0.2445152848958969
+max_scaled_mean_absolute_error:
+- 0.5499318242073059
+- 0.526858925819397
+- 0.5314342379570007
+- 0.5090692639350891
+- 0.5471025705337524
+max_scaled_root_mean_squared_error:
+- 2.152407646179199
+- 2.086804151535034
+- 1.7959694862365723
+- 1.8397164344787598
+- 2.167043924331665
+max_val_loss:
+- 0.13089171051979065
+- 0.162700816988945
+- 0.2097165733575821
+- 0.22333891689777374
+- 0.1497689187526703
+max_val_scaled_mean_absolute_error:
+- 0.2929815948009491
+- 0.35185784101486206
+- 0.40016210079193115
+- 0.4373350143432617
+- 0.33035120368003845
+max_val_scaled_root_mean_squared_error:
+- 1.40901517868042
+- 1.7008235454559326
+- 2.9287467002868652
+- 2.566326856613159
+- 1.7031078338623047
+min_learning_rate:
+- 1.0138461220776662e-05
+- 1.0138461220776662e-05
+- 1.0138461220776662e-05
+- 1.0138461220776662e-05
+- 1.0138461220776662e-05
+min_loss:
+- 0.02428211271762848
+- 0.016674185171723366
+- 0.0228374432772398
+- 0.021824872121214867
+- 0.015478077344596386
+min_scaled_mean_absolute_error:
+- 0.05441948026418686
+- 0.03624086454510689
+- 0.04346726834774017
+- 0.04265357553958893
+- 0.03468232601881027
+min_scaled_root_mean_squared_error:
+- 0.8370198607444763
+- 0.5666390657424927
+- 0.5970380306243896
+- 0.9158002138137817
+- 0.6234539151191711
+min_val_loss:
+- 0.10598661750555038
+- 0.13624021410942078
+- 0.1740884929895401
+- 0.19378630816936493
+- 0.1220226138830185
+min_val_scaled_mean_absolute_error:
+- 0.23816289007663727
+- 0.2950071096420288
+- 0.3316235840320587
+- 0.3795801103115082
+- 0.2742084562778473
+min_val_scaled_root_mean_squared_error:
+- 1.14818274974823
+- 1.536876916885376
+- 2.6274499893188477
+- 2.450216054916382
+- 1.0961058139801025
+model_class: make_crystal_model
+model_name: NMPN
+model_version: '2023-11-22'
+multi_target_indices: null
+number_histories: 5
+scaled_mean_absolute_error:
+- 0.05466507747769356
+- 0.037272896617650986
+- 0.04410763457417488
+- 0.04297201335430145
+- 0.034941498190164566
+scaled_root_mean_squared_error:
+- 0.8370198607444763
+- 0.5668810606002808
+- 0.5970380306243896
+- 0.9158002138137817
+- 0.623555600643158
+seed: 42
+time_list:
+- '2:40:33.267353'
+- '2:39:53.846892'
+- '2:41:34.925130'
+- '2:41:45.267930'
+- '2:39:32.728305'
+val_loss:
+- 0.12087029963731766
+- 0.14805226027965546
+- 0.19250518083572388
+- 0.20443375408649445
+- 0.1289469599723816
+val_scaled_mean_absolute_error:
+- 0.2714456021785736
+- 0.3209201991558075
+- 0.3672274649143219
+- 0.4004261791706085
+- 0.28424978256225586
+val_scaled_root_mean_squared_error:
+- 1.288943886756897
+- 1.6749753952026367
+- 2.7677669525146484
+- 2.512850522994995
+- 1.1402829885482788
diff --git a/training/results/MatProjectDielectricDataset/NMPN_make_crystal_model/NMPN_hyper.json b/training/results/MatProjectDielectricDataset/NMPN_make_crystal_model/NMPN_hyper.json
new file mode 100644
index 00000000..e7a790d2
--- /dev/null
+++ b/training/results/MatProjectDielectricDataset/NMPN_make_crystal_model/NMPN_hyper.json
@@ -0,0 +1 @@
+{"model": {"class_name": "make_crystal_model", "module_name": "kgcnn.literature.NMPN", "config": {"name": "NMPN", "inputs": [{"shape": [null], "name": "node_number", "dtype": "int64", "ragged": true}, {"shape": [null, 3], "name": "node_coordinates", "dtype": "float32", "ragged": true}, {"shape": [null, 2], "name": "range_indices", "dtype": "int64", "ragged": true}, {"shape": [null, 3], "name": "range_image", "dtype": "int64", "ragged": true}, {"shape": [3, 3], "name": "graph_lattice", "dtype": "float32", "ragged": false}], "input_tensor_type": "ragged", "input_embedding": null, "input_node_embedding": {"input_dim": 95, "output_dim": 64}, "input_edge_embedding": {"input_dim": 5, "output_dim": 64}, "set2set_args": {"channels": 32, "T": 3, "pooling_method": "sum", "init_qstar": "0"}, "pooling_args": {"pooling_method": "mean"}, "use_set2set": true, "depth": 3, "node_dim": 128, "verbose": 10, "geometric_edge": true, "make_distance": true, "expand_distance": true, "output_embedding": "graph", "output_mlp": {"use_bias": [true, true, false], "units": [25, 25, 1], "activation": ["selu", "selu", "linear"]}}}, "training": {"cross_validation": {"class_name": "KFold", "config": {"n_splits": 5, "random_state": 42, "shuffle": true}}, "fit": {"batch_size": 16, "epochs": 700, "validation_freq": 10, "verbose": 2, "callbacks": [{"class_name": "kgcnn>LinearLearningRateScheduler", "config": {"learning_rate_start": 0.0001, "learning_rate_stop": 1e-05, "epo_min": 50, "epo": 700, "verbose": 0}}]}, "compile": {"optimizer": {"class_name": "Adam", "config": {"learning_rate": 0.0001}}, "loss": "mean_absolute_error"}, "scaler": {"class_name": "StandardLabelScaler", "module_name": "kgcnn.data.transform.scaler.standard", "config": {"with_std": true, "with_mean": true, "copy": true}}, "multi_target_indices": null}, "data": {}, "info": {"postfix": "", "postfix_file": "", "kgcnn_version": "4.0.0"}, "dataset": {"class_name": "MatProjectDielectricDataset", "module_name": "kgcnn.data.datasets.MatProjectDielectricDataset", "config": {}, "methods": [{"map_list": {"method": "set_range_periodic", "max_distance": 5.0}}]}}
\ No newline at end of file
diff --git a/training/results/MatProjectJdft2dDataset/NMPN_make_crystal_model/NMPN_MatProjectJdft2dDataset_score.yaml b/training/results/MatProjectJdft2dDataset/NMPN_make_crystal_model/NMPN_MatProjectJdft2dDataset_score.yaml
new file mode 100644
index 00000000..581f262e
--- /dev/null
+++ b/training/results/MatProjectJdft2dDataset/NMPN_make_crystal_model/NMPN_MatProjectJdft2dDataset_score.yaml
@@ -0,0 +1,156 @@
+OS: posix_linux
+backend: tensorflow
+cuda_available: 'True'
+data_unit: meV/atom
+date_time: '2023-12-22 10:25:12'
+device_id: '[LogicalDevice(name=''/device:CPU:0'', device_type=''CPU''), LogicalDevice(name=''/device:GPU:0'',
+  device_type=''GPU'')]'
+device_memory: '[]'
+device_name: '[{}, {''compute_capability'': (8, 0), ''device_name'': ''NVIDIA A100
+  80GB PCIe''}]'
+epochs:
+- 700
+- 700
+- 700
+- 700
+- 700
+execute_folds: null
+kgcnn_version: 4.0.0
+learning_rate:
+- 1.0138461220776662e-05
+- 1.0138461220776662e-05
+- 1.0138461220776662e-05
+- 1.0138461220776662e-05
+- 1.0138461220776662e-05
+loss:
+- 0.04172148182988167
+- 0.03481512516736984
+- 0.04141012579202652
+- 0.02786765992641449
+- 0.025851132348179817
+max_learning_rate:
+- 9.999999747378752e-05
+- 9.999999747378752e-05
+- 9.999999747378752e-05
+- 9.999999747378752e-05
+- 9.999999747378752e-05
+max_loss:
+- 0.4462912678718567
+- 0.4646398723125458
+- 0.4499674439430237
+- 0.4077697694301605
+- 0.4537045657634735
+max_scaled_mean_absolute_error:
+- 64.89154052734375
+- 64.6207275390625
+- 61.12132263183594
+- 52.67870330810547
+- 53.9419059753418
+max_scaled_root_mean_squared_error:
+- 148.22642517089844
+- 143.38377380371094
+- 139.44029235839844
+- 130.7115020751953
+- 122.01180267333984
+max_val_loss:
+- 0.3362121284008026
+- 0.360738068819046
+- 0.44887232780456543
+- 0.5983206629753113
+- 0.5939966440200806
+max_val_scaled_mean_absolute_error:
+- 48.74551010131836
+- 50.49139404296875
+- 61.520694732666016
+- 77.21085357666016
+- 71.298828125
+max_val_scaled_root_mean_squared_error:
+- 111.84777069091797
+- 108.81877899169922
+- 140.4239501953125
+- 180.51446533203125
+- 186.91348266601562
+min_learning_rate:
+- 1.0138461220776662e-05
+- 1.0138461220776662e-05
+- 1.0138461220776662e-05
+- 1.0138461220776662e-05
+- 1.0138461220776662e-05
+min_loss:
+- 0.04117120802402496
+- 0.03436309099197388
+- 0.04115643352270126
+- 0.025716491043567657
+- 0.024806268513202667
+min_scaled_mean_absolute_error:
+- 5.984552383422852
+- 4.812740325927734
+- 5.638136863708496
+- 3.290254831314087
+- 2.961510181427002
+min_scaled_root_mean_squared_error:
+- 53.575157165527344
+- 54.29600524902344
+- 67.30669403076172
+- 18.282670974731445
+- 19.062496185302734
+min_val_loss:
+- 0.2205861359834671
+- 0.2674580216407776
+- 0.36657559871673584
+- 0.4271361827850342
+- 0.5461778044700623
+min_val_scaled_mean_absolute_error:
+- 31.981548309326172
+- 37.38349914550781
+- 50.25608825683594
+- 55.208736419677734
+- 65.52993774414062
+min_val_scaled_root_mean_squared_error:
+- 60.30561828613281
+- 94.90013885498047
+- 125.50224304199219
+- 149.50657653808594
+- 172.7936553955078
+model_class: make_crystal_model
+model_name: NMPN
+model_version: '2023-11-22'
+multi_target_indices: null
+number_histories: 5
+scaled_mean_absolute_error:
+- 6.065205097198486
+- 4.877674579620361
+- 5.672479152679443
+- 3.5663793087005615
+- 3.0853846073150635
+scaled_root_mean_squared_error:
+- 53.78377151489258
+- 54.29600524902344
+- 67.3075180053711
+- 18.33293342590332
+- 19.069774627685547
+seed: 42
+time_list:
+- '0:09:36.046237'
+- '0:09:30.023669'
+- '0:09:33.995009'
+- '0:09:30.808331'
+- '0:09:31.685247'
+val_loss:
+- 0.3332675099372864
+- 0.3471689224243164
+- 0.4061582088470459
+- 0.5812740325927734
+- 0.5781887769699097
+val_scaled_mean_absolute_error:
+- 48.31858444213867
+- 48.600467681884766
+- 55.65491485595703
+- 74.98410034179688
+- 69.43495178222656
+val_scaled_root_mean_squared_error:
+- 106.09896850585938
+- 105.8543701171875
+- 131.84280395507812
+- 173.60345458984375
+- 180.57183837890625
diff --git a/training/results/MatProjectJdft2dDataset/NMPN_make_crystal_model/NMPN_hyper.json b/training/results/MatProjectJdft2dDataset/NMPN_make_crystal_model/NMPN_hyper.json
new file mode 100644
index 00000000..832f808e
--- /dev/null
+++ b/training/results/MatProjectJdft2dDataset/NMPN_make_crystal_model/NMPN_hyper.json
@@ -0,0 +1 @@
+{"model": {"class_name": "make_crystal_model", "module_name": "kgcnn.literature.NMPN", "config": {"name": "NMPN", "inputs": [{"shape": [null], "name": "node_number", "dtype": "int64", "ragged": true}, {"shape": [null, 3], "name": "node_coordinates", "dtype": "float32", "ragged": true}, {"shape": [null, 2], "name": "range_indices", "dtype": "int64", "ragged": true}, {"shape": [null, 3], "name": "range_image", "dtype": "int64", "ragged": true}, {"shape": [3, 3], "name": "graph_lattice", "dtype": "float32", "ragged": false}], "input_tensor_type": "ragged", "input_embedding": null, "input_node_embedding": {"input_dim": 95, "output_dim": 64}, "input_edge_embedding": {"input_dim": 5, "output_dim": 64}, "set2set_args": {"channels": 32, "T": 3, "pooling_method": "sum", "init_qstar": "0"}, "pooling_args": {"pooling_method": "mean"}, "use_set2set": true, "depth": 3, "node_dim": 128, "verbose": 10, "geometric_edge": true, "make_distance": true, "expand_distance": true, "output_embedding": "graph", "output_mlp": {"use_bias": [true, true, false], "units": [25, 25, 1], "activation": ["selu", "selu", "linear"]}}}, "training": {"cross_validation": {"class_name": "KFold", "config": {"n_splits": 5, "random_state": 42, "shuffle": true}}, "fit": {"batch_size": 16, "epochs": 700, "validation_freq": 10, "verbose": 2, "callbacks": [{"class_name": "kgcnn>LinearLearningRateScheduler", "config": {"learning_rate_start": 0.0001, "learning_rate_stop": 1e-05, "epo_min": 50, "epo": 700, "verbose": 0}}]}, "compile": {"optimizer": {"class_name": "Adam", "config": {"learning_rate": 0.0001}}, "loss": "mean_absolute_error"}, "scaler": {"class_name": "StandardLabelScaler", "module_name": "kgcnn.data.transform.scaler.standard", "config": {"with_std": true, "with_mean": true, "copy": true}}, "multi_target_indices": null}, "data": {}, "info": {"postfix": "", "postfix_file": "", "kgcnn_version": "4.0.0"}, "dataset": {"class_name": "MatProjectJdft2dDataset", "module_name": "kgcnn.data.datasets.MatProjectJdft2dDataset", "config": {}, "methods": [{"map_list": {"method": "set_range_periodic", "max_distance": 5.0}}]}}
\ No newline at end of file
diff --git a/training/results/QM7Dataset/EGNN/EGNN_QM7Dataset_score.yaml b/training/results/QM7Dataset/EGNN/EGNN_QM7Dataset_score.yaml
new file mode 100644
index 00000000..d905db3d
--- /dev/null
+++ b/training/results/QM7Dataset/EGNN/EGNN_QM7Dataset_score.yaml
@@ -0,0 +1,155 @@
+OS: posix_linux
+backend: tensorflow
+cuda_available: 'True'
+data_unit: kcal/mol
+date_time: '2023-12-21 18:02:50'
+device_id: '[LogicalDevice(name=''/device:CPU:0'', device_type=''CPU''), LogicalDevice(name=''/device:GPU:0'',
+  device_type=''GPU'')]'
+device_memory: '[]'
+device_name: '[{}, {''compute_capability'': (7, 0), ''device_name'': ''Tesla V100-SXM2-32GB''}]'
+epochs:
+- 800
+- 800
+- 800
+- 800
+- 800
+execute_folds: null
+kgcnn_version: 4.0.0
+learning_rate:
+- 1.06999996205559e-05
+- 1.06999996205559e-05
+- 1.06999996205559e-05
+- 1.06999996205559e-05
+- 1.06999996205559e-05
+loss:
+- 0.004870810080319643
+- 0.0046996125020086765
+- 0.005611352156847715
+- 0.0050828722305595875
+- 0.004682221449911594
+max_learning_rate:
+- 0.0005000000237487257
+- 0.0005000000237487257
+- 0.0005000000237487257
+- 0.0005000000237487257
+- 0.0005000000237487257
+max_loss:
+- 0.5422196984291077
+- 0.5268594622612
+- 0.6562739610671997
+- 0.5407633781433105
+- 0.7496322393417358
+max_scaled_mean_absolute_error:
+- 121.36742401123047
+- 117.94087219238281
+- 147.26658630371094
+- 121.25706481933594
+- 168.2179718017578
+max_scaled_root_mean_squared_error:
+- 182.41380310058594
+- 168.71316528320312
+- 253.0386962890625
+- 181.5135040283203
+- 289.64056396484375
+max_val_loss:
+- 0.19889870285987854
+- 0.1781025379896164
+- 0.1769949048757553
+- 0.202616885304451
+- 0.1932889223098755
+max_val_scaled_mean_absolute_error:
+- 45.23289108276367
+- 40.74118423461914
+- 39.89699172973633
+- 45.87350082397461
+- 43.905029296875
+max_val_scaled_root_mean_squared_error:
+- 77.23835754394531
+- 87.74166870117188
+- 89.57672882080078
+- 76.53211975097656
+- 86.95550537109375
+min_learning_rate:
+- 1.06999996205559e-05
+- 1.06999996205559e-05
+- 1.06999996205559e-05
+- 1.06999996205559e-05
+- 1.06999996205559e-05
+min_loss:
+- 0.0048573813401162624
+- 0.0046996125020086765
+- 0.0052500017918646336
+- 0.004842739086598158
+- 0.004682221449911594
+min_scaled_mean_absolute_error:
+- 1.089234471321106
+- 1.0534539222717285
+- 1.17666757106781
+- 1.083858847618103
+- 1.0508092641830444
+min_scaled_root_mean_squared_error:
+- 1.9792815446853638
+- 2.192974805831909
+- 2.152200222015381
+- 2.1958253383636475
+- 2.143144369125366
+min_val_loss:
+- 0.006939230486750603
+- 0.007709983736276627
+- 0.008420325815677643
+- 0.007248176261782646
+- 0.007352082524448633
+min_val_scaled_mean_absolute_error:
+- 1.5553877353668213
+- 1.7484978437423706
+- 1.9094713926315308
+- 1.6285290718078613
+- 1.6690664291381836
+min_val_scaled_root_mean_squared_error:
+- 4.739010810852051
+- 3.862034797668457
+- 9.905815124511719
+- 4.142892360687256
+- 2.8325278759002686
+model_class: make_model
+model_name: EGNN
+model_version: '2023-12-04'
+multi_target_indices: null
+number_histories: 5
+scaled_mean_absolute_error:
+- 1.092336893081665
+- 1.0534539222717285
+- 1.2578788995742798
+- 1.1378531455993652
+- 1.0508092641830444
+scaled_root_mean_squared_error:
+- 1.9884182214736938
+- 2.192974805831909
+- 2.2176666259765625
+- 2.2220873832702637
+- 2.143144369125366
+seed: 42
+time_list:
+- '0:15:55.618355'
+- '0:15:49.520512'
+- '0:15:47.567017'
+- '0:16:01.803663'
+- '0:15:47.088854'
+val_loss:
+- 0.006939230486750603
+- 0.007709983736276627
+- 0.008650460280478
+- 0.007632002234458923
+- 0.007352082524448633
+val_scaled_mean_absolute_error:
+- 1.5553877353668213
+- 1.7484978437423706
+- 1.9632694721221924
+- 1.7136964797973633
+- 1.6690664291381836
+val_scaled_root_mean_squared_error:
+- 4.806612491607666
+- 3.862034797668457
+- 9.99007511138916
+- 4.142892360687256
+- 2.8325278759002686
diff --git a/training/results/QM7Dataset/EGNN/EGNN_hyper.json b/training/results/QM7Dataset/EGNN/EGNN_hyper.json
new file mode 100644
index 00000000..90b5ee12
--- /dev/null
+++ b/training/results/QM7Dataset/EGNN/EGNN_hyper.json
@@ -0,0 +1 @@
+{"model": {"class_name": "make_model", "module_name": "kgcnn.literature.EGNN", "config": {"name": "EGNN", "inputs": [{"shape": [null], "name": "node_number", "dtype": "int64", "ragged": true}, {"shape": [null, 3], "name": "node_coordinates", "dtype": "float32", "ragged": true}, {"shape": [null], "name": "edge_number", "dtype": "int64", "ragged": true}, {"shape": [null, 2], "name": "edge_indices", "dtype": "int64", "ragged": true}], "input_tensor_type": "ragged", "input_embedding": null, "input_node_embedding": {"input_dim": 95, "output_dim": 64}, "input_edge_embedding": {"input_dim": 95, "output_dim": 64}, "depth": 4, "node_mlp_initialize": null, "use_edge_attributes": true, "edge_mlp_kwargs": {"units": [64, 64], "activation": ["swish", "linear"]}, "edge_attention_kwargs": null, "use_normalized_difference": false, "expand_distance_kwargs": null, "coord_mlp_kwargs": {"units": [64, 1], "activation": ["swish", "linear"]}, "pooling_coord_kwargs": {"pooling_method": "mean"}, "pooling_edge_kwargs": {"pooling_method": "sum"}, "node_normalize_kwargs": null, "node_mlp_kwargs": {"units": [64, 64], "activation": ["swish", "linear"]}, "use_skip": true, "verbose": 10, "node_pooling_kwargs": {"pooling_method": "sum"}, "output_embedding": "graph", "output_to_tensor": true, "output_mlp": {"use_bias": [true, true], "units": [64, 1], "activation": ["swish", "linear"]}}}, "training": {"fit": {"batch_size": 64, "epochs": 800, "validation_freq": 10, "verbose": 2, "callbacks": [{"class_name": "kgcnn>LinearLearningRateScheduler", "config": {"learning_rate_start": 0.0005, "learning_rate_stop": 1e-05, "epo_min": 100, "epo": 800, "verbose": 0}}]}, "compile": {"optimizer": {"class_name": "Adam", "config": {"learning_rate": 0.0005}}, "loss": "mean_absolute_error"}, "scaler": {"class_name": "QMGraphLabelScaler", "config": {"atomic_number": "node_number", "scaler": [{"class_name": "StandardLabelScaler", "config": {"with_std": true, "with_mean": true, "copy": true}}]}}, "multi_target_indices": null}, "data": {"data_unit": "kcal/mol"}, "info": {"postfix": "", "postfix_file": "", "kgcnn_version": "4.0.0"}, "dataset": {"class_name": "QM7Dataset", "module_name": "kgcnn.data.datasets.QM7Dataset", "config": {}, "methods": [{"map_list": {"method": "set_range", "max_distance": 4, "max_neighbours": 10000}}]}}
\ No newline at end of file
diff --git a/training/results/QM7Dataset/PAiNN/PAiNN_QM7Dataset_score.yaml b/training/results/QM7Dataset/PAiNN/PAiNN_QM7Dataset_score.yaml
new file mode 100644
index 00000000..83188307
--- /dev/null
+++ b/training/results/QM7Dataset/PAiNN/PAiNN_QM7Dataset_score.yaml
@@ -0,0 +1,137 @@
+OS: posix_linux
+backend: tensorflow
+cuda_available: 'True'
+data_unit: kcal/mol
+date_time: '2023-12-21 16:40:27'
+device_id: '[LogicalDevice(name=''/device:CPU:0'', device_type=''CPU''), LogicalDevice(name=''/device:GPU:0'',
+  device_type=''GPU'')]'
+device_memory: '[]'
+device_name: '[{}, {''compute_capability'': (7, 0), ''device_name'': ''Tesla V100-SXM2-32GB''}]'
+epochs:
+- 872
+- 872
+- 872
+- 872
+- 872
+execute_folds: null
+kgcnn_version: 4.0.0
+loss:
+- 0.0025554883759468794
+- 0.003069676226004958
+- 0.0023232335224747658
+- 0.0018510563531890512
+- 0.0034466360229998827
+max_loss:
+- 0.3588047921657562
+- 0.38279712200164795
+- 0.33286476135253906
+- 0.36403176188468933
+- 0.38951554894447327
+max_scaled_mean_absolute_error:
+- 80.50007629394531
+- 85.8753890991211
+- 74.6446533203125
+- 81.73396301269531
+- 87.41252136230469
+max_scaled_root_mean_squared_error:
+- 119.15148162841797
+- 127.15708923339844
+- 111.88113403320312
+- 124.43669891357422
+- 128.63967895507812
+max_val_loss:
+- 0.11566412448883057
+- 0.22171451151371002
+- 0.11109314113855362
+- 0.09779135137796402
+- 0.06699567288160324
+max_val_scaled_mean_absolute_error:
+- 25.87778091430664
+- 49.55368423461914
+- 24.82270622253418
+- 21.888626098632812
+- 15.00621223449707
+max_val_scaled_root_mean_squared_error:
+- 33.36971664428711
+- 53.28633117675781
+- 29.97235107421875
+- 24.47319221496582
+- 19.686246871948242
+min_loss:
+- 0.0016856554429978132
+- 0.0015430744970217347
+- 0.0015242404770106077
+- 0.0018510563531890512
+- 0.0016132221790030599
+min_scaled_mean_absolute_error:
+- 0.37848562002182007
+- 0.34577375650405884
+- 0.34190860390663147
+- 0.41577157378196716
+- 0.3627304434776306
+min_scaled_root_mean_squared_error:
+- 0.5201364755630493
+- 0.46305033564567566
+- 0.4779084026813507
+- 0.5605447888374329
+- 0.49603137373924255
+min_val_loss:
+- 0.00735496636480093
+- 0.006994512863457203
+- 0.0064369081519544125
+- 0.006740586832165718
+- 0.0068360986188054085
+min_val_scaled_mean_absolute_error:
+- 1.6508293151855469
+- 1.569486379623413
+- 1.4454553127288818
+- 1.513767957687378
+- 1.5344483852386475
+min_val_scaled_root_mean_squared_error:
+- 7.693243503570557
+- 4.385979652404785
+- 7.473199844360352
+- 3.0994436740875244
+- 2.897643566131592
+model_class: make_model
+model_name: PAiNN
+model_version: '2023-10-04'
+multi_target_indices: null
+number_histories: 5
+scaled_mean_absolute_error:
+- 0.5739108324050903
+- 0.6887179613113403
+- 0.5221326351165771
+- 0.41577157378196716
+- 0.7747818231582642
+scaled_root_mean_squared_error:
+- 0.7554106712341309
+- 0.8686598539352417
+- 0.6846397519111633
+- 0.5605447888374329
+- 0.9511976838111877
+seed: 42
+time_list:
+- '0:47:27.132277'
+- '0:47:44.092972'
+- '0:47:52.275830'
+- '0:48:39.693941'
+- '0:48:18.381033'
+val_loss:
+- 0.007661634124815464
+- 0.006994512863457203
+- 0.006724040489643812
+- 0.006898249499499798
+- 0.0068360986188054085
+val_scaled_mean_absolute_error:
+- 1.7198737859725952
+- 1.569486379623413
+- 1.5101431608200073
+- 1.548624873161316
+- 1.5344483852386475
+val_scaled_root_mean_squared_error:
+- 8.332200050354004
+- 4.385979652404785
+- 7.6372528076171875
+- 3.0994436740875244
+- 2.897643566131592
diff --git a/training/results/QM7Dataset/PAiNN/PAiNN_hyper.json b/training/results/QM7Dataset/PAiNN/PAiNN_hyper.json
new file mode 100644
index 00000000..16f57623
--- /dev/null
+++ b/training/results/QM7Dataset/PAiNN/PAiNN_hyper.json
@@ -0,0 +1 @@
+{"model": {"class_name": "make_model", "module_name": "kgcnn.literature.PAiNN", "config": {"name": "PAiNN", "inputs": [{"shape": [null], "name": "node_number", "dtype": "int64", "ragged": true}, {"shape": [null, 3], "name": "node_coordinates", "dtype": "float32", "ragged": true}, {"shape": [null, 2], "name": "range_indices", "dtype": "int64", "ragged": true}], "input_tensor_type": "ragged", "input_embedding": null, "input_node_embedding": {"input_dim": 95, "output_dim": 128}, "equiv_initialize_kwargs": {"dim": 3, "method": "eps"}, "bessel_basis": {"num_radial": 20, "cutoff": 5.0, "envelope_exponent": 5}, "pooling_args": {"pooling_method": "sum"}, "conv_args": {"units": 128, "cutoff": null}, "update_args": {"units": 128}, "depth": 3, "verbose": 10, "output_embedding": "graph", "output_mlp": {"use_bias": [true, true], "units": [128, 1], "activation": ["swish", "linear"]}}}, "training": {"fit": {"batch_size": 32, "epochs": 872, "validation_freq": 10, "verbose": 2, "callbacks": []}, "compile": {"optimizer": {"class_name": "Adam", "config": {"learning_rate": {"class_name": "kgcnn>LinearWarmupExponentialDecay", "config": {"learning_rate": 0.001, "warmup_steps": 150.0, "decay_steps": 200000.0, "decay_rate": 0.01}}, "amsgrad": true, "use_ema": true}}, "loss": "mean_absolute_error"}, "scaler": {"class_name": "QMGraphLabelScaler", "config": {"atomic_number": "node_number", "scaler": [{"class_name": "StandardLabelScaler", "config": {"with_std": true, "with_mean": true, "copy": true}}]}}, "multi_target_indices": null}, "data": {"data_unit": "kcal/mol"}, "info": {"postfix": "", "postfix_file": "", "kgcnn_version": "4.0.0"}, "dataset": {"class_name": "QM7Dataset", "module_name": "kgcnn.data.datasets.QM7Dataset", "config": {}, "methods": [{"map_list": {"method": "set_range", "max_distance": 5, "max_neighbours": 10000}}]}}
\ No newline at end of file
diff --git a/training/results/README.md b/training/results/README.md
index 81d1d7ff..07341f8f 100644
--- a/training/results/README.md
+++ b/training/results/README.md
@@ -57,6 +57,7 @@ ESOL consists of 1128 compounds as smiles and their corresponding water solubili
 | model       | kgcnn   |   epochs | MAE [log mol/L]        | RMSE [log mol/L]       |
 |:------------|:--------|---------:|:-----------------------|:-----------------------|
 | AttentiveFP | 4.0.0   |      200 | 0.4351 ± 0.0110     | 0.6080 ± 0.0207     |
+| CMPNN       | 4.0.0   |      600 | 0.5276 ± 0.0154     | 0.7505 ± 0.0189     |
 | DGIN        | 4.0.0   |      300 | 0.4434 ± 0.0252     | 0.6225 ± 0.0420     |
 | DMPNN       | 4.0.0   |      300 | 0.4401 ± 0.0165     | 0.6203 ± 0.0292     |
 | EGNN        | 4.0.0   |      800 | 0.4507 ± 0.0152     | 0.6563 ± 0.0370     |
@@ -151,9 +152,13 @@ Energies and forces for molecular dynamics trajectories. All geometries in A, en
 
 Materials Project dataset from Matbench with 4764 crystal structures and their corresponding Refractive index (unitless). We use a random 5-fold cross-validation. 
 
-| model                     | kgcnn   |   epochs | MAE [no unit]          | RMSE [no unit]         |
-|:--------------------------|:--------|---------:|:-----------------------|:-----------------------|
-| Schnet.make_crystal_model | 4.0.0   |      800 | **0.3180 ± 0.0359** | **1.8509 ± 0.5854** |
+| model                        | kgcnn   |   epochs | MAE [no unit]          | RMSE [no unit]         |
+|:-----------------------------|:--------|---------:|:-----------------------|:-----------------------|
+| CGCNN.make_crystal_model     | 4.0.0   |     1000 | 0.3306 ± 0.0602     | 1.9736 ± 0.7324     |
+| DimeNetPP.make_crystal_model | 4.0.0   |      780 | 0.3415 ± 0.0542     | 1.9637 ± 0.6323     |
+| Megnet.make_crystal_model    | 4.0.0   |     1000 | 0.3362 ± 0.0550     | 2.0156 ± 0.5872     |
+| NMPN.make_crystal_model      | 4.0.0   |      700 | 0.3289 ± 0.0489     | 1.8770 ± 0.6522     |
+| Schnet.make_crystal_model    | 4.0.0   |      800 | **0.3180 ± 0.0359** | **1.8509 ± 0.5854** |
 
 #### MatProjectEFormDataset
 
@@ -188,6 +193,7 @@ Materials Project dataset from Matbench with 636 crystal structures and their co
 | CGCNN.make_crystal_model     | 4.0.0   |     1000 | 57.6974 ± 18.0803     | 140.6167 ± 44.8418     |
 | DimeNetPP.make_crystal_model | 4.0.0   |      780 | 50.2880 ± 11.4199     | 126.0600 ± 38.3769     |
 | Megnet.make_crystal_model    | 4.0.0   |     1000 | 51.1735 ± 9.1746      | 123.4178 ± 32.9582     |
+| NMPN.make_crystal_model      | 4.0.0   |      700 | 59.3986 ± 10.9272     | 139.5943 ± 32.1129     |
 | PAiNN.make_crystal_model     | 4.0.0   |      800 | 49.3889 ± 11.5376     | 121.7087 ± 30.0472     |
 | Schnet.make_crystal_model    | 4.0.0   |      800 | **45.2412 ± 11.6395** | **115.6890 ± 39.0929** |
 
@@ -266,11 +272,15 @@ TUDataset of proteins that are classified as enzymes or non-enzymes. Nodes repre
 
 QM7 dataset is a subset of GDB-13. Molecules of up to 23 atoms (including 7 heavy atoms C, N, O, and S), totalling 7165 molecules. We use dataset-specific 5-fold cross-validation. The atomization energies are given in kcal/mol and are ranging from -800 to -2000 kcal/mol). 
 
-| model   | kgcnn   |   epochs | MAE [kcal/mol]         | RMSE [kcal/mol]        |
-|:--------|:--------|---------:|:-----------------------|:-----------------------|
-| Megnet  | 4.0.0   |      800 | **1.5180 ± 0.0802** | **3.0321 ± 0.1936** |
-| NMPN    | 4.0.0   |      500 | 7.2907 ± 0.9061     | 38.1446 ± 12.1445   |
-| Schnet  | 4.0.0   |      800 | 3.4313 ± 0.4757     | 10.8978 ± 7.3863    |
+| model     | kgcnn   |   epochs | MAE [kcal/mol]         | RMSE [kcal/mol]        |
+|:----------|:--------|---------:|:-----------------------|:-----------------------|
+| DimeNetPP | 4.0.0   |      872 | 3.4639 ± 0.2003     | 7.5327 ± 1.8190     |
+| EGNN      | 4.0.0   |      800 | 1.7300 ± 0.1336     | 5.1268 ± 2.5134     |
+| Megnet    | 4.0.0   |      800 | 1.5180 ± 0.0802     | 3.0321 ± 0.1936     |
+| MXMNet    | 4.0.0   |      900 | **1.2431 ± 0.0820** | **2.6694 ± 0.2584** |
+| NMPN      | 4.0.0   |      500 | 7.2907 ± 0.9061     | 38.1446 ± 12.1445   |
+| PAiNN     | 4.0.0   |      872 | 1.5765 ± 0.0742     | 5.2705 ± 2.2848     |
+| Schnet    | 4.0.0   |      800 | 3.4313 ± 0.4757     | 10.8978 ± 7.3863    |
 
 #### QM9Dataset