Comments (6)
jbloomAus
commented on July 30, 2024
LN and Adam done. No clear benefit on smaller model. I think I'll get everything implemented then set off some sweeps tomorrow/the next day with the memory env environment.
from decisiontransformerinterpretability.
jbloomAus
commented on July 30, 2024
done lr scheduling stuff: https://github.com/users/jbloomAus/projects/1/views/1?pane=issue&itemId=27012682
from decisiontransformerinterpretability.
jbloomAus
commented on July 30, 2024
I'm going to add a task here for setting up wandb sweeps. I think given the stuff I've added, it's important to just get a better sense of the right hyperparameters I need.
from decisiontransformerinterpretability.
jbloomAus
commented on July 30, 2024
I just had a lightbulb moment relating to #61 so I'm going to do that really quick before I attempt wandb sweeps.
from decisiontransformerinterpretability.
jbloomAus
commented on July 30, 2024
converting "Implement masking rather than just having different tokens during padding" to it's own card.
from decisiontransformerinterpretability.
jbloomAus
commented on July 30, 2024
Closing this. Got working agents!
from decisiontransformerinterpretability.
Related Issues (20)
- Cuda cannot be disabled HOT 3
- Over resource limits on Streamlit Cloud
- Over resource limits on Streamlit Cloud
- Train a BC on PCT traj = 1 with two different agents mixed in and see if we can tell which one it thinks it is.
- Facelift of the RTG Scan in the streamlit app HOT 1
- Improve history panel in streamlit app HOT 1
- SVD Decomp / Explore ways to use dimensionality reduction to quickly understand what heads are doing. HOT 1
- Make it possible to track the preferences of the PPO in the app. HOT 1
- Folding Layer Norm in Model Loading HOT 9
- Implement AVEC in the interpretability app HOT 2
- Streamlit app requires mujoco installation
- Write a post before EAG London HOT 2
- Expand analytical AVEC
- Look into why MemoryDT appears to have no bias on the value terms. HOT 1
- Reverse Logit Lense
- Complete Embedding visualizations
- Shapley Values on Attention Heads or Causal Edges Via Ablation
- Fix Ablation Tool
- Complete QK/OV Circuit visualizations
- "Algebraic value editing" raises exception 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 decisiontransformerinterpretability.