Update README.md

README.md

@@ -126,18 +126,18 @@ Evaluation was performed at regular intervals, with the best model selected base
 | Model                     | BACE↑  | BBBP↑  | TOX21↑ | HIV↑   | SIDER↑ | CLINTOX↑ |
 | ------------------------- | ------ | ------ | ------ | ------ | ------ | -------- |
 | **Tasks**                 | 1      | 1      | 12     | 1      | 27     | 2        |
-| Derify/ChemBERTa-druglike | 0.8008 | 0.7418 | 0.7548 | 0.7744 | 0.6313 | 0.9621   |
+| Derify/ChemBERTa_augmented_pubchem_13m | 0.8008 | 0.7418 | 0.7548 | 0.7744 | 0.6313 | 0.9621   |
 
 ### Regression Datasets (RMSE - Lower is better)
 
 | Model                     | ESOL↓  | FREESOLV↓ | LIPO↓  | BACE↓  | CLEARANCE↓ |
 | ------------------------- | ------ | --------- | ------ | ------ | ---------- |
 | **Tasks**                 | 1      | 1         | 1      | 1      | 1          |
-| Derify/ChemBERTa-druglike | 0.8798 | 0.5282    | 0.6853 | 0.9554 | 45.4362    |
+| Derify/ChemBERTa_augmented_pubchem_13m | 0.8798 | 0.5282    | 0.6853 | 0.9554 | 45.4362    |
 
 Benchmarks were conducted using the [chemberta3](https://github.com/deepforestsci/chemberta3) framework. 
 Datasets were split with DeepChem’s scaffold splits and filtered to include only molecules with SMILES length ≤200, following MolFormer paper's recommendation. 
-The ChemBERTa-druglike model was fine-tuned for 100 epochs with a learning rate of 3e-5 and batch size of 32. 
+The model was fine-tuned for 100 epochs with a learning rate of 3e-5 and batch size of 32. 
 Each task was run with 3 different random seeds, and the mean performance is reported.
 
 ## References