Comments (2)
Hi @iliaschalkidis,
you can use train_model
with from transformer.train import train_model
and define a non token-level Task
and train the model on your sentence-level task(which uses [CLS]
internally)
you can take a look at tutorial.ipynb and read this in code.
from bert-keras.
Hi @Separius, this looks really promising. Although I want to build something more complicated (custom), so I am going to read your code for train_model
and start prototyping my model based on these principles.
I wish Google had already port BERT into tensorhub and made it as easy to use as ELMo tensorhub module.
Thanks a lot for your quick response! Have a great week!
from bert-keras.
Related Issues (20)
- How can I apply BERT to a cloze task? HOT 2
- Possible inconsistency in how ids are used for text encoders HOT 8
- Some issues when using training and lm_gen HOT 1
- ValueError: You need tensorflow >= 1.3 for better keras tpu support! HOT 4
- Fine-tuning BERT-keras HOT 9
- Poor performance and poor results HOT 5
- What's the meaning of TextEncoder.BERT_SPECIAL_COUNT, TextEncoder.TextEncoder.BERT_UNUSED_COUNT HOT 4
- loss does not decrease during training HOT 1
- Error in tutorial notebook HOT 4
- number of trainable parameters HOT 1
- Error while compiling the model after loading the google-BERT model on tpu HOT 2
- unknown field name "training_sentence_size" in TrainerSpec. HOT 4
- BERT on TPU or GPU? HOT 4
- Does it have chinese version? HOT 1
- how to run code on GPU
- How to set up reading comprehension for BERT Keras
- Error while compiling on TPU HOT 1
- any plan to use Colab & TPU? HOT 3
- error of sparse_categorical_crossentropy when using theano backend HOT 5
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 bert-keras.