tharun66/Mistral-7B-Text2SQL

1---2base_model: mistralai/Mistral-7B-Instruct-v0.33datasets:4- generator5library_name: peft6license: apache-2.07tags:8- trl9- sft10- generated_from_trainer11model-index:12- name: Mistral-7B-Text2SQL13  results: []14---15 16<!-- This model card has been generated automatically according to the information the Trainer had access to. You17should probably proofread and complete it, then remove this comment. -->18 19# Mistral-7B-Text2SQL20 21This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the generator dataset.22It achieves the following results on the evaluation set:23- Loss: 0.464324 25## Model description26 27This repository contains a fine-tuned version of the Mistral 7B model, tailored specifically for text-to-SQL tasks.28The model is designed to convert natural language queries into structured SQL queries, enabling seamless interaction with databases through conversational language.29 30## Intended uses & limitations31 32The Mistral-7B-Text2SQL model is intended for applications that require converting natural language queries into SQL commands. Suitable use cases include:33 34Conversational Agents: Allowing users to retrieve information from databases through natural language interaction.35Data Analytics: Enabling non-technical users to query databases without needing to know SQL syntax.36Business Intelligence: Supporting decision-making processes by simplifying data access.37 38## Training and evaluation data39 40The model was fine-tuned using the generator dataset, which consists of a variety of natural language queries paired with corresponding SQL commands. The dataset is designed to cover a wide range of query types, allowing the model to generalize better across different types of SQL queries.41 42Dataset Characteristics43Diversity: The dataset includes examples from various domains, ensuring that the model learns to handle a broad spectrum of queries.44Size: (Include the size of the dataset, e.g., the number of examples if available.)45Annotations: Each example includes natural language input along with the expected SQL output, facilitating supervised learning.46 47 48 49### Training results50 51| Training Loss | Epoch | Step | Validation Loss |52|:-------------:|:-----:|:----:|:---------------:|53| 1.8346        | 0.4   | 10   | 0.7031          |54| 0.5882        | 0.8   | 20   | 0.5273          |55| 0.487         | 1.2   | 30   | 0.4850          |56| 0.4423        | 1.6   | 40   | 0.4675          |57| 0.4235        | 2.0   | 50   | 0.4564          |58| 0.3464        | 2.4   | 60   | 0.4690          |59| 0.3411        | 2.8   | 70   | 0.4643          |60 61 62### Framework versions63 64- PEFT 0.13.265- Transformers 4.45.266- Pytorch 2.4.1+cu12167- Datasets 3.0.168- Tokenizers 0.20.1