Comments (1)
This is a bit too slow (almost like CPU speed). Were you training on GPU and what's your system config? There could be some compatibility issue that forced the code to resort to CPU on some latest GPUs (e.g. 3090). This sort of warnings/issues wouldn't have been captured by the log so you might need to look at some console log.
For the steps, what we observe is that with the default setting the performance started to flatten after 200k steps. Note though in general the more steps the better (e.g. 1-2 points increase for another 200k steps), as shown by several previous works.
from graph2smiles.
Related Issues (8)
- inconsistent results in the paper HOT 1
- reaction prediction HOT 3
- Why pad `a_graph` and `b_graph` to length 11? HOT 1
- I encountered a problem while training the model. HOT 1
- Raw data (how clean and token) HOT 3
- About training time for USPTO-480K HOT 10
- Pretrained model arguments mismatch the dataset name and expected output size HOT 2
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 graph2smiles.