Update hyperparameter and metric info in README.md

README.md

@@ -20,10 +20,10 @@ model-index:
       type: polite-guard
     metrics:
     - type: accuracy
-      value: 92.2
+      value: 92.4
       name: Accuracy
     - type: f1
-      value: 92.2
+      value: 92.4
       name: F1 Score
 ---
 # Polite Guard
@@ -31,8 +31,8 @@ model-index:
 - **Model type**: BERT* (Bidirectional Encoder Representations from Transformers)  
 - **Architecture**: Fine-tuned [BERT-base uncased](https://huggingface.co/bert-base-uncased)
 - **Task**: Text Classification
-- **Source Code**: (https://github.com/intel/polite-guard)
-- **Dataset**: (https://huggingface.co/datasets/Intel/polite-guard)
+- **Source Code**: https://github.com/intel/polite-guard
+- **Dataset**: https://huggingface.co/datasets/Intel/polite-guard
 
 **Polite Guard** is an open-source NLP language model developed by Intel, fine-tuned from BERT for text classification tasks. It is designed to classify text into four categories: polite, somewhat polite, neutral, and impolite. This model, along with its [accompanying datasets](https://huggingface.co/datasets/Intel/polite-guard) and [source code](https://github.com/intel/polite-guard), is available on Hugging Face* and GitHub* to enable both communities to contribute to developing more sophisticated and context-aware AI systems.
 
@@ -62,7 +62,7 @@ By ensuring respectful and polite interactions on various platforms, Polite Guar
 
 |Hypeparameter|Batch size|Learning rate|Learning rate schedule          |Max epochs|Optimizer|Weight decay|Precision |
 |-------------|----------|-------------|--------------------------------|----------|---------|------------|----------|
-|Value        |32        |   2.90e-5   |Linear warmup (10% of steps)    |  2       | AdamW   |  0.0003    |bf16-mixed|
+|Value        |32        |   4.78e-05  |Linear warmup (10% of steps)    |  2       | AdamW   |  1.01e-06  |bf16-mixed|
 
 Hyperparameter tuning was performed using Bayesian optimization with the Tree-structured Parzen Estimator (TPE) algorithm through Optuna* with 35 trials to maximize the validation F1-score. The hyperparameter search space included 
 
@@ -82,8 +82,8 @@ The code for the synthetic data generation and fine-tuning can be found [here](h
 
 Here are the key performance metrics of the model on the test dataset containing both synthetic and manually annotated data:
 
-- **Accuracy**: 92.2% on the Polite Guard test dataset.
-- **F1-Score**: 92.2% on the Polite Guard test dataset.
+- **Accuracy**: 92.4% on the Polite Guard test dataset.
+- **F1-Score**: 92.4% on the Polite Guard test dataset.
 
 ## How to Use