Comments (2)
Hi Tim, thank you for your prompt reply!
At the moment I'm running a training on FB15K; I'm going to check what happens around 600 epochs then.
I'm going to close this issue (since there is not a real "issue" with the model).
In case I need more info, can I contact you at the email address in the ConvE paper?
Thanks again for your kindness!
from conve.
Unfortunately, I did not record the exact number of epochs. The logs have some detail, but they are outdated since they came from before the bugfix in #18. However, the logs might still show you a reasonable number of epochs to run for a model. Note that some logs are split into multiple runs (FB15k) where I resume the checkpoint and train a bit more multiple times.
For the evaluation procedure, I would record the test score associated with the highest validation score. The number of epochs changes from dataset to dataset but usually I run until I do not see any reasonable increases in validation set performance. For some datasets this can be a lot of epochs, for example, I think on FB15k it ranged into about 600 epochs or so since you see still tiny but steady improvements after many epochs. For FB15k-237 you see a maximum validation score at a lot smaller number of epochs — I do not remember the exact number, but it was in the range of 40-60 epochs I think.
Let me know if you need more info in general or on any dataset.
from conve.
Related Issues (20)
- Why the left and right results differ so much? HOT 1
- What's the meaning about param 'samples_per_fille' in preprocess? Will it influence the train set? HOT 1
- changing embedding-dim HOT 1
- about evaluation sort part question HOT 2
- question about the model of the convE HOT 2
- How can I solve this problem? HOT 1
- question about the num_entities and num_relations?
- Question about the ETA HOT 1
- Question about the batch-size
- YAGO dataset
- Log info
- Can I use more network layers?
- How does the model implement negative sampling?
- What meaning is Hits@10 left and right? HOT 1
- i want ro run on colab how should i do that HOT 1
- About the activation function HOT 2
- About the indegree HOT 1
- About spaCy
- Validation and test exits with "^C" HOT 1
- About keys meaning
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 conve.