Comments (5)
First try: dropout = 0.1. Run: lunar-serenity-26.
from platalea.
Promising, surely better results than with 0 dropout. Now trying dropout = 0.2
: dark-serenity-27. Note: this is only dropout in the transformer encoder layer.
from platalea.
Also tried 0.5 (worthy-sunset-28). Both cases: difference between validation loss and step loss stays slightly lower initially than in the lower dropout factor runs.
However, also running logical-butterfly-29 and there we see that after some more training the validation loss still starts climbing again, whereas the training loss more or less completely vanishes, so again overfit on training set at some point. The performance is better though, and still climbing at this moment (epoch 130 of 300), so let's see where it goes.
from platalea.
We did a sweep again over dropout values and again values between 0.2-0.5 seem to perform best. However, validation loss still increases in all runs after a certain time.
As already mentioned in this report, we should probably look into more regularization options to correct for this overfitting on training data. See #61.
from platalea.
I think we solved the validation loss (overfitting) issue during our regularization sweeps (https://wandb.ai/spokenlanguage/platalea_transformer/reports/Jan-29-Project-Update-Regularization-rates-conclusion--Vmlldzo0MzY3MDg).
from platalea.
Related Issues (20)
- Reproduce label_encoders.pkl HOT 3
- [ZRVG] CPC feature extraction
- Merge zerospeech21-vg branch? HOT 4
- add to RSD HOT 1
- Add issue template
- Create a conda package HOT 1
- Consider creating a conda channel HOT 1
- Use static analysis/code quality service HOT 2
- Description of the software HOT 1
- Supported platform HOT 1
- Add code of conduct
- Add code documentation HOT 1
- No help message when mandatory argument is missing. HOT 2
- CI fails HOT 3
- Test case with SpokenCOCO dataset
- Store dtype in metadata of memmap
- Versioning, releasing, DOI, Zenodo HOT 7
- Linting
- Fix warnings about code quality
- Add reference documentation
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 platalea.