Update README.md

README.md

@@ -33,7 +33,7 @@ This is the model card of a 🤗 transformers model that has been pushed on the
 - **Architecture:** The model is based on the T5 architecture, which employs a transformer-based neural network. Transformers have proven effective for various natural language processing (NLP) tasks due to their attention mechanisms and ability to capture contextual information.
 - **Task:** The primary purpose of this model is lecture summarization. Given a lecture or a longer text, it aims to generate a concise summary that captures the essential points. This can be valuable for students, researchers, or anyone seeking condensed information.
 - **Input Format:** The model expects input in a text-to-text format. Specifically, you provide a prompt (e.g., the lecture content) and specify the desired task (e.g., “summarize”). The model then generates a summary as the output.
-- **Fine-Tuning:** The Lucas-Hyun-Lee/T5_small_lecture_summarization model has likely undergone fine-tuning on lecture-specific data. During fine-tuning, it learns to optimize its parameters for summarization by minimizing a loss function.
+- **Fine-Tuning:** The Lucas-Hyun-Lee/T5_small_lecture_summarization model has undergone fine-tuning on bbc-news data. During fine-tuning, it learns to optimize its parameters for summarization by minimizing a loss function.
 - **Model Size:** As the name suggests, this is a small-sized variant of T5. Smaller models are computationally efficient and suitable for scenarios where memory or processing power is limited.
 - **Performance:** The model’s performance depends on the quality and diversity of the training data, as well as the specific lecture content it encounters during fine-tuning. It should be evaluated based on metrics such as ROUGE (Recall-Oriented Understudy for Gisting Evaluation) scores.