Comments (4)
younesbelkada
commented on June 28, 2024
Hi @Galaxy-Husky
Thanks for the issue, I think this is the wrong dataset format, can you try for example with this one: https://huggingface.co/datasets/trl-internal-testing/Anthropic-hh-rlhf-processed ?
from trl.
Galaxy-Husky
commented on June 28, 2024
Hi @Galaxy-Husky Thanks for the issue, I think this is the wrong dataset format, can you try for example with this one: https://huggingface.co/datasets/trl-internal-testing/Anthropic-hh-rlhf-processed ?
Thank you for your prompt reply!
It works with the version 0.8.1. But It appears to be much smaller than the original dataset, which is Anthropic/hh-rlhf.
Is there a dataset of the same size as the original one?
from trl.
Yuancheng-Xu
commented on June 28, 2024
@Galaxy-Husky Here? https://huggingface.co/datasets/trl-internal-testing/hh-rlhf-trl-style
from trl.
Galaxy-Husky
commented on June 28, 2024
@Galaxy-Husky Here? https://huggingface.co/datasets/trl-internal-testing/hh-rlhf-trl-style
Thank you for your reply! But the version 0.8.1 only accepts this https://huggingface.co/datasets/trl-internal-testing/Anthropic-hh-rlhf-processed, which is different from trl-internal-testing/hh-rlhf-trl-style in format.
from trl.
Related Issues (20)
- Reproducing LLaVA with Mistral backened
- Bug in calling model.eval() in PPO
- vsft_llava.py:
- Fail to train with ORPOTrainer under multi-GPUs setting HOT 8
- NameError: name 'PeftConfig' is not defined HOT 4
- Loss value returned by the SFT Trainer
- Using PEFT causes model to not predict EOS
- Using SFTTrainer and the DeepSpeed Zero-3 Method training, the data map function runs, but the map function does not run in parallel GPU form. HOT 1
- IPO loss computation vs changes in DPO dataset format
- Anthropic HH new dataset format repeats the prompt HOT 1
- Group Relative Policy Optimization Trainer
- bugs in trained save and evaluation for DPO training with deepspeed_zero3 HOT 3
- config.json file is missing. HOT 3
- The data is consuming too much GPU memory In the SFTTrainer HOT 2
- [Question] Does TRL support DPO trainer with simulated environment for generating training data like PPO's step-based training?
- [Question]How should I combine DPOTrainer and Accelerate for training?
- CLI utils class cases seem to be incorrect HOT 2
- Training stops early
- Bug: `tests` are being included in package HOT 1
- [enhancement] Implement IRPO training custom loss 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 trl.