- Introduction
- Setting up your account
- Balance
- Clusters
- Concept drift
- Coverage
- Datasets
- General fields
- Labels (predictions, confidence levels, label hierarchy, and label sentiment)
- Models
- Streams
- Model Rating
- Projects
- Precision
- Recall
- Annotated and unannotated messages
- Extraction Fields
- Sources
- Taxonomies
- Training
- True and false positive and negative predictions
- Validation
- Messages
- Access control and administration
- Manage sources and datasets
- Understanding the data structure and permissions
- Creating or deleting a data source in the GUI
- Preparing data for .CSV upload
- Uploading a CSV file into a source
- Creating a dataset
- Multilingual sources and datasets
- Enabling sentiment on a dataset
- Amending dataset settings
- Deleting a message
- Deleting a dataset
- Exporting a dataset
- Using Exchange integrations
- Model training and maintenance
- Understanding labels, general fields, and metadata
- Label hierarchy and best practices
- Comparing analytics and automation use cases
- Turning your objectives into labels
- Overview of the model training process
- Generative Annotation
- Dastaset status
- Model training and annotating best practice
- Training with label sentiment analysis enabled
- Understanding data requirements
- Train
- Introduction to Refine
- Precision and recall explained
- Precision and Recall
- How validation works
- Understanding and improving model performance
- Reasons for label low average precision
- Training using Check label and Missed label
- Training using Teach label (Refine)
- Training using Search (Refine)
- Understanding and increasing coverage
- Improving Balance and using Rebalance
- When to stop training your model
- Using general fields
- Generative extraction
- Using analytics and monitoring
- Automations and Communications Mining™
- Developer
- Uploading data
- Downloading data
- Exchange Integration with Azure service user
- Exchange Integration with Azure Application Authentication
- Exchange Integration with Azure Application Authentication and Graph
- Fetching data for Tableau with Python
- Elasticsearch integration
- General field extraction
- Self-hosted Exchange integration
- UiPath® Automation Framework
- UiPath® official activities
- How machines learn to understand words: a guide to embeddings in NLP
- Prompt-based learning with Transformers
- Efficient Transformers II: knowledge distillation & fine-tuning
- Efficient Transformers I: attention mechanisms
- Deep hierarchical unsupervised intent modelling: getting value without training data
- Fixing annotating bias with Communications Mining™
- Active learning: better ML models in less time
- It's all in the numbers - assessing model performance with metrics
- Why model validation is important
- Comparing Communications Mining™ and Google AutoML for conversational data intelligence
- Licensing
- FAQs and more
Communications Mining user guide
Model rollback
The model rollback feature allows you to revert back to a previous version of your model. This way, you can reset the training data, for both label and general field annotations, to the annotations used to train this model version.
You can only roll back to pinned model versions.
Using model rollback
The model rollback icon is available on the Models page, on all pinned model versions.
To use the model rollback feature, proceed as follows:
-
Select the rollback icon on the model version you want to revert back to.
Note:The current trained model version will automatically be pinned as a backup but any annotations captured by a model version that is currently still training will be lost.
-
Once you select the rollback button, a pop-up window appears as a reminder that you are recommended to allow the current model version to finish training before rolling your model back. To proceed, select Reset.
If the model rollback has started successfully, a banner will appear on the page.
What happens during the model rollback
While the model is rolling back, you cannot modify the dataset. This means that you cannnot train your model during this time, and apply any labels or general fields to messages.
A warning indicator will show up at the top, informing you that the model is being rolled back.
If you try to modify your dataset, the following banner will appear on the page, and any messages we try to annotate will not have the label or general field applied to it until the model rollback has complete.
Although the rollback feature helps you roll back to a previous version of a model, if you have made any major mistakes in our model training, you should not rely too much on it.
Instead, make sure that you follow the proper model training methodology correctly the first time, as this can save us time in the long-run.