Comments (5)
For the quality-based classification, it is data point character level filtering.
from sotopia-pi.
Note that the quality should be based on environment + agent (in the same environment, one agent may produce quality data while the other may not).
from sotopia-pi.
Currently, we add quality filtering by using the goal score in rewards for each episode logs. The idea is that, for a given dialogue, we use the average goal scores to determine if this dialogue is considered "good" in achieving the goal. For all dialogues within the same scenario, we use the average goal score to determine its relative stand. If the average goal score for a dialogue is below the scenario average, we should remove it, UNLESS the scenario average is too high (such as 10).
To avoid removing dialogues with high goal score but stand relatively low in the scenario, we use 7 as a lower bound threshold. If a dialogue's avg score is above 7, regardless of its stand in the scenario, we are going to include the dialogue.
Note that 7 comes from observing the distribution of easy scenario, and for now, we apply the same threshold for our testing data which contains hard scenario. It might worth lower the bar for hard scenario [DISCUSSION].
By using 7 threshold, we reduce 450 dialogues to 388 dialogues.
from sotopia-pi.
For the code we apply the filtering, it currently sits in https://github.com/XuhuiZhou/sotopia/tree/feature/log-filtering-for-ft. We are considering copy the main function/building blocks from sotopia and rather have these files on our sotopia-llm-ft repo, but this copy/paste has not been executed yet.
from sotopia-pi.
Finish in #58
from sotopia-pi.
Related Issues (20)
- [BUG]: Fix and replace the uncleaned "Agent1" and "Agent2" appeared in the scenario and social goal
- [FEAT]: Build human evaluation pipeline HOT 1
- [BUG]: Data Directory deleted from /llm_ft
- [FEAT]: Create new scenarios based on new inspirational prompts
- [FEAT]: Implement Automated Self-Training Pipeline HOT 1
- [FEAT]: Self-Train Pipeline Backbone
- [FEAT]: Intermediate saves of checkpoints in sft trainer
- [FEAT]: Automated uploading to gcp storage
- [FEAT]: Self-Train Pipeline on Babel HOT 1
- [FEAT]: adding gcloud utils for upload, download, and check metadata
- [FEAT]: Training Pipeline with Improve Steps
- [FEAT]: Modularize codebase for self-training
- [FEAT]: Save full model during training
- [FEAT]: Changes to custom callbacks to accomodate fastchat deploy
- [FEAT]: Add Monitor to Eval Step Results HOT 1
- [FEAT]: Launch a human evaluation report based on Prolific HOT 2
- [FEAT]: Add interactive demo
- [FEAT]: Add jupyter notebook demo HOT 2
- [BUG]: Behavior cloning can not be reproduced
- [BUG]: Questions about the size of the dataset.
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 sotopia-pi.