Comments (4)
I've confirmed that there is an issue with train_shallow_layer.py
. Specifically the test I ran was to run both train.py
(nl2sql) and train_shallow_layer.py
overnight. The nl2sql model reached 80% accuracy after 12 epochs, while the shallow-layer model remained at 0% even after 21 epochs of training. CLI parameters for both were the same.
Any ideas on what might be causing train_shallow_layer.py
to fail?
from sqlova.
Hi @hanrelan
That may be caused by using improper learning rate. In shallow layer
, args.lr is used to train BERT (sorry for the confusion) and 1e-3 is too fast.. I have modified the code to avoid confusion. Please try again with same command (note that args.lr is not used anymore in train_shallow_layer.py
0e1794f).
Thanks!
Wonseok
from sqlova.
Ah, makes sense, thanks. I'll try it again tonight and close this issue if it works
from sqlova.
That fixed it, getting 78% lx accuracy now. Thanks!
from sqlova.
Related Issues (20)
- For real industrial application, what strategy to locate the exact table? HOT 1
- How to fine tune sequence-to-SQL?
- How do I use predict.py for custom data? HOT 2
- weird error occurs when run predict.py
- Testing models with predict.py does not give me any results file HOT 1
- Need of results_train.jsonl
- Standford coreNLP
- Training on custom data HOT 4
- Replicating dev results on BERT base
- Training doesn't run + how to predict with custom query? HOT 1
- Keras implementation of Column Attention
- Error with annotate_ws.py HOT 7
- Isuue in utlis.wikisql.py
- TypeError: 'Document' object is not iterable
- There is insufficient memory during training, and the get_wemb_bert function call in the train function applies for a lot of memory
- dbengine HOT 5
- How to use RoBERTa instead of BERT ?
- How can I evaluate the pre-trained model on WikiSQL? HOT 1
- Question about the human eval result, thank you. HOT 2
- No module named 'matplotlib' after I download matplotlib
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 sqlova.