Update README.md

README.md

@@ -14,6 +14,8 @@ tags:
 - madgrad
 pipeline_tag: text-classification
 library_name: transformers
+base_model: gbyuvd/chemselfies-base-bertmlm
+base_model_relation: finetune
 ---
 
 # ChemFIE-SA (ChemSELFIES - Synthesis Accessibility)
@@ -165,11 +167,11 @@ The model (currently only trained on the 1st chunk) was evaluated using four tes
 
 A comprehensive set of metrics employed to evaluate the model's performance:
 
-1. **Accuracy (ACC)**: Overall correctness of predictions
-2. **Recall**: Ability to identify all relevant instances (sensitivity)
-3. **Precision**: Accuracy of positive predictions
-4. **F1-score**: Harmonic mean of precision and recall
-5. **Area Under the Receiver Operating Characteristic curve (AUROC)**: Model's ability to distinguish between classes
+1. **Accuracy (ACC)**
+2. **Recall**
+3. **Precision**
+4. **F1-score**
+5. **Area Under the Receiver Operating Characteristic curve (AUROC)**
 
 All metrics were evaluated using a threshold of 0.50 for binary classification.
 
@@ -190,7 +192,7 @@ Comparison data is sourced from Wang et al. (2023), used various models as encod
 
 which was trained/fine-tuned to predict based on SMILES - while ChemFIE-SA is SELFIES-based:
 
-| **Model**            | **Recall** | **Precision** | **F–score** | **AUROC** |
+| **Model**            | **Recall** | **Precision** |    **F1**   | **AUROC** |
 | -------------------- | :--------: | :-----------: | :---------: | :-------: |
 | DeepSA_DeBERTa       |   0.873    |     0.920     |    0.896    |   0.959   |
 | DeepSA_GraphCodeBert |   0.931    |     0.944     |    0.937    |   0.987   |