Comments (5)
jacobweiss2305
commented on May 19, 2024
What is the .947 mean? Maybe there is a formula you can point us to,?
from promptbench.
jacobweiss2305
commented on May 19, 2024
It looks like a standard accuracy metric. How many the bot answered correctly divide by total responses?
The data is pre-labelled so thats my best guess.
from promptbench.
Millz98
commented on May 19, 2024
What is the .947 mean? Maybe there is a formula you can point us to,?
That looks like an accuracy score
from promptbench.
Millz98
commented on May 19, 2024
It looks like a standard accuracy metric. How many the bot answered correctly divide by total responses?
The data is pre-labelled so thats my best guess.
Yes reviewing the code you showed it seems to be the prediction score with an accuracy of 94% on each section it is evaluating.
from promptbench.
Immortalise
commented on May 19, 2024
Hi, Millz98 is right, 0.947 means accuracy of this prompt.
from promptbench.
Related Issues (20)
- Interpretation of attack results HOT 2
- Enhancement Proposal for Dynamic Evaluation Framework Integration HOT 2
- How to add a new Model HOT 2
- Parsing the output of a model HOT 3
- The change in the 'api_key' parameter has not been reflected in the documentation and tutorials. HOT 2
- The link is broken in https://llm-eval.github.io/pages/code.html HOT 1
- Is this an ongoing project? HOT 2
- Where is defined inference_total_dataset() HOT 1
- How do you get the evaluation results of the `prompt enginering` leaderboard? HOT 4
- The `prompt engineering` leaderboard is cut off in half... HOT 5
- Is ` DyVal` included in `PromptBench` yet? HOT 2
- The ‘temperature’ parameter in pb.LLMModel needs to be of type float HOT 1
- Can you provide a general data format for constructing test data independently? HOT 1
- How to reproduce the transferability results? HOT 1
- typo HOT 1
- Compatibility Request: Upgrade openai Dependency to Support >=1.10.0
- Access to per-sample evaluation results HOT 1
- examples basic.ipyn
- Pip's dependency conflicts :datasets==2.15.0
- can you share a prompt to test llama with mmlu data ?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from promptbench.