Comments (5)
By default, the training will run for 500,000 steps.
For the quickstart this value is indeed way too high and we don't expect users to run the full training (we should probably add a note!). The quickstart is mostly meant to showcase a minimal configuration and the main command lines.
When training on real data, this default value is more reasonable and the training could indeed take days. However, there are options to automatically stop the training earlier, but they are not enabled by default.
from opennmt-tf.
Thanks for a quick reply. Yes, I think a notice about expectations would be helpful. Usually, toy examples are very quick to run and evaluate. Perhaps also with some expectations about the output, so you know what you should be getting if OpenNMT runs correctly.
Presumably, one can abort training at any time and just evaluate any of the saved checkpoints?
from opennmt-tf.
Presumably, one can abort training at any time and just evaluate any of the saved checkpoints?
Yes.
from opennmt-tf.
Just to show you what I mean with expected output, what I am getting from 70k steps of training is so garbled that I am worried that something with the software installation has gone wrong. Perhaps ballparking BLEU results is an option?
$ head -n 5 src-test.txt tgt-test.txt pred-ckpt-70k.txt
==> src-test.txt <==
Orlando Bloom and Miranda Kerr still love each other
Actors Orlando Bloom and Model Miranda Kerr want to go their separate ways .
However , in an interview , Bloom has said that he and Kerr still love each other .
Miranda Kerr and Orlando Bloom are parents to two-year-old Flynn .
Actor Orlando Bloom announced his separation from his wife , supermodel Miranda Kerr .
==> tgt-test.txt <==
Orlando Bloom und Miranda Kerr lieben sich noch immer
Schauspieler Orlando Bloom und Model Miranda Kerr wollen künftig getrennte Wege gehen .
In einem Interview sagte Bloom jedoch , dass er und Kerr sich noch immer lieben .
Miranda Kerr und Orlando Bloom sind Eltern des zweijährigen Flynn .
Schauspieler Orlando Bloom hat sich zur Trennung von seiner Frau , Topmodel Miranda Kerr , geäußert .
==> pred-ckpt-70k.txt <==
und in der , die und alle anderen Techniken verwenden , um jede und , dass Sie auf , und sind , um jede Präfektur und alle in anderen und und und sind noch für sind .
Die Ramblas und des Seehafens von Barcelona .
Das , dass wir in , ist und dass er in und , ohne dass sie erobern müssen .
Die , und , dass sich mit den Eltern schlafen nicht Unterkunft kostenlos !
Die , dass Sie ist , das , , , , , , dass er am 1.1.1993 .
from opennmt-tf.
The dataset used in the quickstart is too small to get anything useful from a Transformer training. We would need to use a bigger training set in order to define an expected BLEU score.
from opennmt-tf.
Related Issues (20)
- xla_ops failed when use multi gpu
- word-level knowledge distillation
- Input size mismatch
- tensorflow lite model example HOT 8
- OpenNMT-tf onnx export ?
- Wrong prediction length from exported OpenNMT-tf models with shared embeddings HOT 1
- Feature Request: Support for TensorFlow 2.14 and Higher
- Multi-source NMT
- cpp for tensorflow serving HOT 2
- SequenceClassifier doesn't seem to learn leaked target HOT 2
- What material did you use to train your pretrained model? HOT 1
- Fine-tune GPT2 model from Transformers HOT 4
- Modify loss function or mask attention in this code HOT 1
- Parallel text inputter fails with compressed text files HOT 1
- An input error occurred while expanding the dataset HOT 1
- ModuleNotFoundError: No module named 'lxml.etree' HOT 1
- Training fails with --mixed_precision and guided alignments
- "Horovod has been shut down" error when training is finished due to early stopping HOT 2
- Make timeout value configurable while searching for an optimal batch size
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 opennmt-tf.