update results of training.

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"]},
             }

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

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}}]}}

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

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}}]}}