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)
- Extending your training section in ReadMe?
- `pip install ochat` - name 'nvcc_cuda_version' is not defined HOT 4
- In the Web UI: https://openchat.team/, how can we specify "condition": "Math Correct"?
- Could the idea of Self-Play Fine-Tuning be used in C-RLFT?
- API token HOT 1
- The AI on the site openchat.team is down HOT 1
- the website requires an openAI API key to work HOT 2
- the model of Pre-tokenized dataset openchat_v3.2_super.train.parquet is Llama2 or Mistral? HOT 1
- HjsonDecodeError("Bad key name (eof)", s, end) during training HOT 3
- distill openchat
- Does the current ochat.training_deepspeed.train only train v.3.2? How to train v.3.5? HOT 1
- How to finetune openchat for downstream apps?
- Cannot create data file
- Exception in ASGI application HOT 1
- I tried to pre-tokeinzation but failed
- run multiple instances on a single gpu
- What is the meaning of padding-free in ReadMe?
- There is a 7B model, good at math: https://github.com/deepseek-ai/DeepSeek-Math.
- Question for https://huggingface.co/openchat/openchat-3.5-0106/blob/main/openchat.json HOT 1
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 openchat.