πΈReviewing Run Analytics
Last updated
Last updated
The Run Analytics page is tailored to offer users real-time observability metrics to track their model's performance over time. It features charts that detail a modelβs latency, token usage, and the associated costs of running inferences. Users can apply filters for different models and tags to specifically analyze latency and cost related to a particular dataset on a selected model.
After assessing the evaluation from the previous step, navigate to the Run Analytics page to see charts on Latency, Cost, Queries, and Tokens for a given time period.
To filter on the runs we ran for this particular example, the following filters would need to be applied:
Start Date
End Date
Model: Mistral, OpenGPT
Tags: CEOs, Example
The page should look something similar to the following screenshots:
Hover over the points on the line graph and bar charts to view detailed information! (example seen in Screenshot #2)
The data from the runs can be viewed at the bottom of the page. This is the same data that can also be viewed on the Prompt Runs page.