Comments (1)
When this parameter is enabled, losses are averaged on a per-sequence basis, otherwise on a per-token basis (same as HF trainer). It is disabled by default because it causes worse results in our experiments, making the model worse at longer responses.
from openchat.
Related Issues (20)
- WARNING: Error in configuration: macro '\frac' failed its substitution!
- weighted_token_accuracy
- about data
- For ๐ปOnline Demo It has been broken out. HOT 2
- Single GPU vs multiple GPU (tensor parallel) suggestion for API Server HOT 3
- repeat the output content until the maximum output length is set HOT 3
- A question about the prefix of only SFT HOT 1
- opchatdataset.estimate_num_batches returns 0 at the beginning of training, and training-stuck problem HOT 1
- use instructor in openchat HOT 1
- huggingface down: openchat can't be started HOT 1
- About performance of LLama (llama2, llama3) model HOT 1
- License needs copyright template filled out
- Why do you also prepend "GPTx" to the "User:"?
- README inconsistency HOT 1
- Using OpenChat 3.6 and the new UI, the web page cannot run properly, and an error code 500 is displayed.
- Qwen 2
- Openchat.team is down again
- TypeError: AsyncLLMEngine.generate() got an unexpected keyword argument 'prompt' HOT 1
- Openchat is freezing HOT 1
- How to do c-RLFT? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from openchat.