> For the complete documentation index, see [llms.txt](https://docs.docbits.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.docbits.com/administration-and-setup/settings/global-settings/document-types/model-training/troubleshooting.md). # Troubleshooting ## Provide solutions to typical problems that can arise during model training, such as data format errors, training model convergence issues, or unexpected model performance degradation. **Here are solutions to some typical problems that can arise during model training:** **Data format errors:** * Make sure the training data is in the correct format and meets the model's requirements. * Check the data for missing values, incorrect encodings, or unexpected structures. * If necessary, convert the data to the correct format and perform preprocessing to ensure it is suitable for training. **Training model convergence issues:** * If the model is struggling to converge or show consistent improvements, check the hyperparameters and training configurations. * Experiment with different learning rates, batch sizes, or optimization algorithms to facilitate convergence. * If necessary, reduce the model complexity or increase the amount of training data to improve model performance. **Unexpected model performance degradation:** * If the model shows unexpectedly poor performance after training, check the training data for possible errors or inaccuracies. * Analyze the error patterns and check if certain classes or features are classified poorly. * Run further tests with new training data to ensure that the model is consistent and reliable. **Overfitting or underfitting:** * Monitor model performance for overfitting or underfitting, which can lead to poor generalization ability. * Experiment with regularization techniques such as L2 regularization or dropout to reduce overfitting. * Increase the amount of training data or data variation to avoid underfitting and improve model performance. **Lack of representativeness of training data:** * Make sure your training data covers a sufficient variety of scenarios and use cases to prepare the model for different situations. * If necessary, supplement the training data with additional examples or synthetic data to improve coverage and increase model performance. By identifying and fixing these issues specifically, you can improve the performance of your model and ensure that it works effectively and reliably to meet the needs of your use case. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.docbits.com/administration-and-setup/settings/global-settings/document-types/model-training/troubleshooting.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.