Comments (3)
junkangwu
commented on September 1, 2024
It could be related to the version of lm-evaluation-harness. For more details, see #12 (comment).
Additionally, after updating the SFT checkpoint from https://huggingface.co/alignment-handbook/zephyr-7b-sft-full, the relative improvement between iteration 0 and iteration 1 appears to be marginal. Are there any new parameter settings being recommended?
from spin.
yinyueqin
commented on September 1, 2024
I use lm-evaluation-harness v0.4.0 for evaluation, which is consistent with the evaluation version used by the author. In addition, the results displayed above are obtained using num_train_epochs=6 for training.
from spin.
AGTSAAA
commented on September 1, 2024
Hi @yinyueqin Have you reproduced the preformance? I also can not reproduce the preformance
from spin.
Related Issues (20)
- the four reward metrics HOT 2
- use_peft Not working? HOT 1
- Potential reason of the significant improvement on the TruthfulQA and GSM8k
- What changes should I make to apply the SPIN method on Llama2?
- GPU Memory question HOT 1
- Thesis discussion: Why can the end-to-end algorithm work properly? HOT 5
- Have you tried combination of SPIN, SFT, DPO
- Confused about iterations HOT 4
- SPIN == DPO in self-iteration? HOT 6
- Question about the checkpoint provided in this repo HOT 3
- Question about using peft (LoRA) HOT 1
- Theoretical Analysis and Idea of SPIN are quite weird (may not make senses)??
- Generate Result
- Cannot reproduce generated samples in UCLA-AGI/SPIN_iter0 HOT 3
- Difference between training / generation input format.
- OOM with 8 A800 HOT 8
- numpy version warnings HOT 1
- Cannot reproduce the result HOT 4
- Hello, I would like to ask, when you are training the model, do you only use the first round of dialogue from the ultrachat_200k?
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 spin.