update results of training. Fix hyper settings.

training/hyper/hyper_mp_perovskites.py

@@ -299,8 +299,8 @@
                     {'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},
+                    {'shape': (3, 3), 'name': 'graph_lattice', 'dtype': 'float64', 'ragged': False},
                     # For `representation="asu"`:
                     # {'shape': (None, 1), 'name': 'multiplicities', 'dtype': 'float32', 'ragged': True},
                     # {'shape': (None, 4, 4), 'name': 'symmops', 'dtype': 'float64', 'ragged': True},

training/hyper/hyper_qm9_energies.py

@@ -419,7 +419,8 @@
                 ]
             },
             # "multi_target_indices": [11]  # 10, 11, 12, 13 = 'U0', 'U', 'H', 'G' or combination
-            "multi_target_indices": target_index
+            # "multi_target_indices": [18]  # 15, 16, 17, 18 = 'U0_atom', 'U_atom', 'H_atom', 'G_atom' or combination
+            "multi_target_indices": [i+5 for i in target_index]
         },
         "data": {
             "dataset": {

training/results/MatProjectPerovskitesDataset/Megnet_make_crystal_model/Megnet_MatProjectPerovskitesDataset_score.yaml

@@ -0,0 +1,156 @@
+OS: posix_linux
+backend: tensorflow
+cuda_available: 'True'
+data_unit: eV/unit_cell
+date_time: '2023-12-29 08:11:00'
+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:
+- 0.004397830925881863
+- 0.005278823431581259
+- 0.004376160446554422
+- 0.004232063423842192
+- 0.004540016874670982
+max_learning_rate:
+- 0.0005000000237487257
+- 0.0005000000237487257
+- 0.0005000000237487257
+- 0.0005000000237487257
+- 0.0005000000237487257
+max_loss:
+- 0.5813741683959961
+- 0.58009934425354
+- 0.5822065472602844
+- 0.5880441665649414
+- 0.5886858105659485
+max_scaled_mean_absolute_error:
+- 0.4308184087276459
+- 0.4286150634288788
+- 0.43322789669036865
+- 0.43700793385505676
+- 0.4390462338924408
+max_scaled_root_mean_squared_error:
+- 0.5738153457641602
+- 0.5650684833526611
+- 0.5685641765594482
+- 0.5760461688041687
+- 0.5783081650733948
+max_val_loss:
+- 0.19459137320518494
+- 0.19005027413368225
+- 0.18510140478610992
+- 0.1782563030719757
+- 0.1876201629638672
+max_val_scaled_mean_absolute_error:
+- 0.14388683438301086
+- 0.14014573395252228
+- 0.13756336271762848
+- 0.1328963190317154
+- 0.14029498398303986
+max_val_scaled_root_mean_squared_error:
+- 0.1895633488893509
+- 0.1875140517950058
+- 0.18289659917354584
+- 0.1750008761882782
+- 0.18676140904426575
+min_learning_rate:
+- 5.549999968934571e-06
+- 5.549999968934571e-06
+- 5.549999968934571e-06
+- 5.549999968934571e-06
+- 5.549999968934571e-06
+min_loss:
+- 0.003926873207092285
+- 0.005278823431581259
+- 0.004338774364441633
+- 0.004204403143376112
+- 0.0040434664115309715
+min_scaled_mean_absolute_error:
+- 0.0029129795730113983
+- 0.0039055212400853634
+- 0.0032300197053700686
+- 0.0031279728282243013
+- 0.0030192884150892496
+min_scaled_root_mean_squared_error:
+- 0.004599509760737419
+- 0.006465458776801825
+- 0.005390344187617302
+- 0.004726039711385965
+- 0.00514197675511241
+min_val_loss:
+- 0.052529748529195786
+- 0.052865125238895416
+- 0.05213373154401779
+- 0.04843062162399292
+- 0.055133167654275894
+min_val_scaled_mean_absolute_error:
+- 0.0389869250357151
+- 0.039114244282245636
+- 0.03883713483810425
+- 0.03578684851527214
+- 0.041139476001262665
+min_val_scaled_root_mean_squared_error:
+- 0.06799951940774918
+- 0.06926962733268738
+- 0.06995909661054611
+- 0.05940646305680275
+- 0.07061677426099777
+model_class: make_crystal_model
+model_name: Megnet
+model_version: '2023-12-05'
+multi_target_indices: null
+number_histories: 5
+scaled_mean_absolute_error:
+- 0.0032622646540403366
+- 0.0039055212400853634
+- 0.0032568767201155424
+- 0.003150396980345249
+- 0.0033899417612701654
+scaled_root_mean_squared_error:
+- 0.005011662840843201
+- 0.006465458776801825
+- 0.005390344187617302
+- 0.004726039711385965
+- 0.005509058944880962
+seed: 42
+time_list:
+- '4:43:57.583793'
+- '4:44:30.393619'
+- '4:50:27.145769'
+- '4:52:04.434260'
+- '4:49:23.093080'
+val_loss:
+- 0.052533868700265884
+- 0.052865125238895416
+- 0.05213373154401779
+- 0.04843062162399292
+- 0.055133167654275894
+val_scaled_mean_absolute_error:
+- 0.0389869250357151
+- 0.039114244282245636
+- 0.03883713483810425
+- 0.03578684851527214
+- 0.041139476001262665
+val_scaled_root_mean_squared_error:
+- 0.06799951940774918
+- 0.06926962733268738
+- 0.06995909661054611
+- 0.05940646305680275
+- 0.07066994905471802

training/results/MatProjectPerovskitesDataset/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": "eV/unit_cell"}, "info": {"postfix": "", "postfix_file": "", "kgcnn_version": "4.0.0"}, "dataset": {"class_name": "MatProjectPerovskitesDataset", "module_name": "kgcnn.data.datasets.MatProjectPerovskitesDataset", "config": {}, "methods": [{"map_list": {"method": "set_range_periodic", "max_distance": 5.0}}]}}

training/results/QM9Dataset/PAiNN/PAiNN_QM9Dataset_score_HOMO.yaml

@@ -0,0 +1,139 @@
+OS: posix_linux
+backend: tensorflow
+cuda_available: 'True'
+data_unit: '[''eV'']'
+date_time: '2023-12-29 08:35:00'
+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:
+- 4
+kgcnn_version: 4.0.0
+loss:
+- 0.003294642549008131
+- 0.0029402414802461863
+- 0.003289161715656519
+- 0.12238723784685135
+- 0.015073779039084911
+max_loss:
+- 0.32262271642684937
+- 0.3293594419956207
+- 0.3262612521648407
+- 50.7930908203125
+- 1.280696988105774
+max_scaled_mean_absolute_error:
+- 0.19472411274909973
+- 0.19837705790996552
+- 0.19602012634277344
+- 30.607391357421875
+- 0.7709271311759949
+max_scaled_root_mean_squared_error:
+- 0.28028348088264465
+- 0.7278462052345276
+- 0.2805926203727722
+- 2517.04052734375
+- 176.50790405273438
+max_val_loss:
+- 0.11736048012971878
+- 0.09089796245098114
+- 0.10240307450294495
+- 0.7400363087654114
+- 0.18249693512916565
+max_val_scaled_mean_absolute_error:
+- 0.07069920748472214
+- 0.054672058671712875
+- 0.061389487236738205
+- 0.44578346610069275
+- 0.10976182669401169
+max_val_scaled_root_mean_squared_error:
+- 0.1011790931224823
+- 0.08075223118066788
+- 0.11302179843187332
+- 0.7455280423164368
+- 0.15606093406677246
+min_loss:
+- 0.0032844471279531717
+- 0.0029378768522292376
+- 0.0032739758025854826
+- 0.10466354340314865
+- 0.015073779039084911
+min_scaled_mean_absolute_error:
+- 0.0019823696929961443
+- 0.001769466558471322
+- 0.0019669937901198864
+- 0.06306608766317368
+- 0.009073719382286072
+min_scaled_root_mean_squared_error:
+- 0.0027461934369057417
+- 0.002509073819965124
+- 0.0026796318124979734
+- 0.09012750536203384
+- 0.022356567904353142
+min_val_loss:
+- 0.048008427023887634
+- 0.05104929953813553
+- 0.049259137362241745
+- 0.16724078357219696
+- 0.0853082463145256
+min_val_scaled_mean_absolute_error:
+- 0.02887205220758915
+- 0.030691467225551605
+- 0.02949574589729309
+- 0.10066147893667221
+- 0.05130166932940483
+min_val_scaled_root_mean_squared_error:
+- 0.054600466042757034
+- 0.05213473364710808
+- 0.05488944053649902
+- 0.19786351919174194
+- 0.083727166056633
+model_class: make_model
+model_name: PAiNN
+model_version: '2023-10-04'
+multi_target_indices:
+- 5
+number_histories: 5
+scaled_mean_absolute_error:
+- 0.0019884807989001274
+- 0.0017709225649014115
+- 0.0019761030562222004
+- 0.07374542206525803
+- 0.009073719382286072
+scaled_root_mean_squared_error:
+- 0.0027565183117985725
+- 0.002510419115424156
+- 0.00269254669547081
+- 0.11067453771829605
+- 0.022356567904353142
+seed: 42
+time_list:
+- '15:01:50.663829'
+- '14:46:45.465706'
+- '15:13:09.007504'
+- '14:47:55.737834'
+- '14:50:00.202334'
+val_loss:
+- 0.048047974705696106
+- 0.051146626472473145
+- 0.049259137362241745
+- 0.16724078357219696
+- 0.08569817245006561
+val_scaled_mean_absolute_error:
+- 0.028896499425172806
+- 0.030748846009373665
+- 0.02949574589729309
+- 0.10066147893667221
+- 0.05154484882950783
+val_scaled_root_mean_squared_error:
+- 0.054600466042757034
+- 0.05233440175652504
+- 0.05574607104063034
+- 0.3130711317062378
+- 0.08536478877067566