training_config.yaml

dataset:
  values_dir_pth: "/path/to/training/values/directory" #Path to the values directory
  headers_dir_pth: "path/to/training/headers/directory" #Path to the attributes directory

data_split:
  train_set: 8000 #Number of csv value-attribute file pairs for training set
  test_set: 100 #Number of csv value-attribute file pairs for testing set
  val_set: 100 #Number of csv value-attribute file pairs for validation set

model:
  hidden_size: 32 #Hidden size for training the model
  dropout_prob: 0.113 #Dropout probability for training the model

training:
  batch_size: 32 #Batch size for training
  num_epochs: 20 #Number of training epochs
  learning_rate: 0.001 #Learning rate of the model
  l2_regularization: 0.001 #L2 regularization strength applied to the optimizer (Avoids overfitting, can be set to 0)
  model_pth: "path/to/custom/trained/model.pth" #Path to where you want to save the custom model
  num_cluster: 3 #Number of clusters for KMeans 
  vectorizer_pth: "path/to/vectorizer.pkl" #Path to where you want to save the Bag of Words vectorizer
  label_encoder_pth: "/path/to/label_encoder.pkl" #Path to where you want to save the Label Encoder
  sentence_transformer_model:  "all-MiniLM-L6-v2" #Name of the sentence transformer model you wish to use fro HuggingFace
  embedding_size: 384 #Dimensionality of the embedding produced by the chosen sentence transformer
  bow_drops: 2 #Number of Bag of Words columns you wish to drop out during the training process (Avoids overfitting, can be set to 0)

visualization:
  accuracy_fig_pth: "/path/to/accuracy_fig.svg" #Path to where you wish to save the Accuracy Curve image
  loss_fig_pth: "/path/to/loss_fig.svg" #Path to where you wish to save the Loss Curve image
  confusion_matrix_fig_pth: "/path/to/confusion_matrix.svg" #Path to where you wish to save the confusion matrix image
  roc_fig_pth: "/path/to/roc_fig.svg" #Path to where you wish to save the ROC curve image