Comments (7)
from da-transformer.
@sdws258 Try removing this line
If it works well, I will update a patch to fix the issue
from da-transformer.
@sdws258 Try removing this line
If it works well, I will update a patch to fix the issue
It looks good to me
from da-transformer.
@sdws258 Try removing this line
If it works well, I will update a patch to fix the issue
yeah, it works
from da-transformer.
I'm sorry that I have another question:
I run the DAG on IWSLT14 ENDE raw data, it appears one warning and causes one error:
Moreover, i find there is no result of IWSLT14 in DAG paper. Please tell me the result of it and how to fix the above problem in DAG.
from da-transformer.
max-source-positions
and max-target-positions
specify the max length of the samples. You should set it according to your dataset.
If you want to train with a sample whose target length is 132, max-target-positions
should be set at least \lambda * 132, i.e., 1056 or larger if lambda=8.
Moreover, dropping some examples does not satisfy the length limitation is normal behavior (your 1st screenshot). But we usually don't drop valid or test samples for fair evaluation (2nd screenshot).
We do not have an official result on IWSLT14 for now. It will be appreciated if you can train a model and tell us your result.
from da-transformer.
Related Issues (12)
- Compiled Failed HOT 6
- model miniaturization HOT 3
- dag_best_alignment: graph size is too small HOT 5
- training config HOT 4
- Can not reproduce the result when factor=4 HOT 7
- The speedup of using the cuda operation compared with PyTorch native operations. HOT 3
- Would you like to share distilled datasets ? HOT 4
- Divide by zero error HOT 2
- Running process stopped at “compiling cuda operations” HOT 5
- can the output model be transform to onnx format? HOT 3
- Pretrained model HOT 2
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 da-transformer.