Comments (1)
Hi,
Thank you for your interest in our dataset!
First of all, the result in your screenshot comes from our ablation study (Appendix E.1.3) that does not remove trailing whitespaces, and it should not be referred to as the most standard evaluation results of the CodeGen model. Please check Table 4 in the main content instead! (and pass rate does increase w.r.t. k)
Second, we've run the experiment multiple times (>=5) and it gives pretty consistent results, i.e., that pass@k stays the same with larger k (>=2). We encourage you to run the experiment to verify. We are also happy to provide the exact prediction file for you to examine.
To give a brief description of why this happens: (1) for most of the examples, pass@k reports 0.0 or 1.0 for all k from 1 to 10, which means either all predictions are correct, or all predictions are incorrect, so that makes no changes in pass rate at different k values; (2) for a small number of cases, only 1 or 2 out of 10 are correct, so that result in the small increase from pass@1 to pass@2.
Hope this provides sufficient information to address your concern!
from odex.
Related Issues (7)
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 odex.