Comments (1)
ZhitingHu
commented on May 9, 2024
2
It's normal in this example. The loss is defined as E_p [R * log p]. When the policy gets stuck in local minima of generating a single token with probability 1 (and generating other tokens with probability 0), the loss = 0. The maximum-entropy regularization can alleviate the issue to some extent.
This is a preliminary example. Usually, we would pre-train the model with cross-entropy loss and fine-tune with policy gradient.
from texar.
Related Issues (20)
- BERT as encoder and a transformer as a decoder. HOT 2
- Is there anyway to empty cache/memory after loading get-2 into our model?
- "infer_greedy" and "infer_sample" for GPT2 Decoder cannot work correctly HOT 2
- How to get the source data set and target set in PairedTextData?
- Is there anyway to train "big data" using transformer? HOT 1
- In Text-Style-Transfer Example, how do you use the model on a chosen sentence? HOT 5
- TypeError: unsupported operand type(s) for +=: 'float' and 'list' HOT 3
- ModuleNotFoundError: No module named 'texar' HOT 1
- ImportError: No module named 'texar.tf' HOT 1
- ERROR: Directory '.' is not installable. Neither 'setup.py' nor 'pyproject.toml' found. HOT 8
- Text Style transfer - Train on my own dataset HOT 4
- save model and predict
- Importing ABC directly from collections will be removed in Python 3.10
- How do I print the output value of the function tx.modules.MLPTransformConnector()
- ASYML project suggestions
- Output is not as expected(style does not getting transferred)
- Question about the installation about the version 0.2.1 HOT 1
- Performance issues in the program
- pip install -e error
- Dependencies in `requirements.txt` have module conflicts.
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 texar.