Update README.md

README.md

@@ -18,9 +18,9 @@ model-index:
       type: text
     metrics:
     - type: accuracy
-      value: 0.7565
+      value: 0.7627
     - type: multiclass_roc_auc
-      value: 0.9096
+      value: 0.9124
 base_model:
 - FacebookAI/roberta-large
 ---
@@ -30,7 +30,7 @@ base_model:
 This repository contains a fine-tuned version of FinBERT (RoBERTa-based) for financial sentiment classification. The model predicts whether a financial news headline or sentence is **positive**, **neutral**, or **negative**.
 
 ## Model Overview
-- **Base model:** FinBERT (RoBERTa)
+- **Base model:** RoBERTa-Large
 - **Task:** Financial sentiment classification (3 classes)
 - **Training data:** Financial news headlines and sentences
 - **Dataset source:** [Kaggle - Finance News Sentiments](https://www.kaggle.com/datasets/antobenedetti/finance-news-sentiments/data?select=dataset.csv)
@@ -40,12 +40,12 @@ This repository contains a fine-tuned version of FinBERT (RoBERTa-based) for fin
   - 2: Positive
 
 ## Evaluation Results
-- **Test Accuracy:** 0.7565
-- **Multiclass ROC AUC (macro-average):** 0.9096
+- **Test Accuracy:** 0.7627
+- **Multiclass ROC AUC (macro-average):** 0.9124
 
 ## Model Folder Structure
 ```
-finbert_finetuned/
+roberta_finance_sentiment/
     config.json
     merges.txt
     model.safetensors
@@ -54,7 +54,7 @@ finbert_finetuned/
     tokenizer.json
     vocab.json
 ```
-**Note:** Only the model files are stored in `finbert_finetuned_news_sentiment/`. Scripts and datasets are kept separate and are not included in this folder or in the model upload.
+**Note:** Only the model files are stored in `roberta_finance_sentiment/`. Scripts and datasets are kept separate and are not included in this folder or in the model upload.
 
 ## How to Use the Fine-Tuned Model
 
@@ -63,7 +63,7 @@ finbert_finetuned/
 import torch
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 # Directory of the model folder
-model_dir = "finbert_finetuned_news_sentiment"
+model_dir = "roberta_finance_sentiment"
 # read the model
 tokenizer = AutoTokenizer.from_pretrained(model_dir)
 model = AutoModelForSequenceClassification.from_pretrained(model_dir)
@@ -82,13 +82,10 @@ print(f"Predicted sentiment: {label_map[pred]}")
 
 ## Notes
 - The model was trained and evaluated on data from the Kaggle dataset linked above.
-- The `finbert_finetuned_news_sentiment/` folder contains only the files needed for inference.
+- The `roberta_finance_sentiment/` folder contains only the files needed for inference.
 - Scripts and datasets are not included in the model folder or in the model upload.
 - For best results, use a GPU for inference if available.
 
-## Citation
-If you use this model, please cite the original [FinBERT paper](https://arxiv.org/abs/2006.08097) and the [Kaggle dataset](https://www.kaggle.com/datasets/antobenedetti/finance-news-sentiments/data?select=dataset.csv).
-
 ---
 
 **Date:** June 2025