Comments (1)
That happens sometimes because the co-training on cross-domain datasets is not always stable, and it happens not only for time series but also on foundation models on other fields. We rerun the experiments when we find nan. You can also adjust the learning rate and use a smaller grad-clip value.
from units.
Related Issues (20)
- How to run self supervised pretraining using UniTS on custom data? HOT 1
- The initialization of Category Embedding HOT 1
- Why there is no loss.backward in training process? HOT 1
- IncompatibleKeys Error when load pre-trained model to do the fine-tuning. HOT 4
- Should requirements.txt be updated including more packages? HOT 2
- Using UniTS on Unlabeled Data for Anomaly Detection Task HOT 2
- Validation set HOT 2
- Dataset Download HOT 1
- A question about fine-tuning
- Using UniTS for new tasks
- gluonts problem HOT 1
- Hello! Asking about Inference. HOT 2
- adjustment for anomaly detection HOT 2
- the meaning of prompt_num HOT 2
- Could you please explain the meaning of prompt token? HOT 3
- About anomaly detection HOT 1
- If the pre-training of UniTS includes a test dataset, can it still be called ZS? HOT 10
- Scripts of single task setting of forecasting
- Can I use other model to replace the UNITS
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 units.