Comments (4)
Thank you!
As the warning:
WARNING:transformers.tokenization_utils_base:Token indices sequence length is longer than the specified maximum sequence length for this model (975 > 512). Running this sequence through the model will result in indexing errors
I agree with you that the sequence is too long for jointBERT model. I will cut too long sentences in jointBERT.
And yes, this is the right approach for training and testing a RL policy from scratch. But as you can see, the system response is too long because your policy outputs too many dialogue acts, which indicates the policy is not well trained.
from convlab-2.
Thank you! I didn't see the warning, it seems it doesn't print on console on Colab.
Another thing I've noticed is that if I train for more epochs (e.g. 1000) the policy loss eventually gets "nan".
Could it be the case that the hyperparameters in the config file aren't the optimal ones? Or are those the same as you've used when reached 0.74 success rate? Cheers!
from convlab-2.
First MLE then PPO: #15 (comment)
Notice: I've improved user agenda policy, so this number may not be accurate, see README https://github.com/thu-coai/ConvLab-2#policy
from convlab-2.
move to #54
from convlab-2.
Related Issues (20)
- [BUG] `try` does NOT work HOT 1
- Training Data HOT 1
- RULEDST evaluation HOT 9
- [Maintenance] pip takes too long in finding boto3 versions (100+ tries & still failed to install) HOT 7
- [BUG] Failed to build agent on CoLab HOT 2
- Spacy latest version compatibility HOT 2
- Different end-to-end results of DAMD HOT 1
- spacy tokenizer HOT 1
- Integrating with my own dataset HOT 3
- [BUG] 关于中文数据集crosswoz上policy-rule代码的问题 HOT 1
- BERTNLU postprocess.py 为什么可以通过 if intent_logits[j] > 0: 来获得intent的预测呢? HOT 2
- [Maintenance] docker for m1 mac, please HOT 1
- Issue in BertNLU HOT 4
- Unable to get the pretrained BERTNLU model. HOT 7
- Unable to get the pretrained BERTNLU model even after updating the URLs HOT 7
- installation python 3.7 on CentOS7 failed[BUG] HOT 2
- The Link to the datasets of LAUG is unreachable HOT 3
- [BUG] Failed to build tokenizers HOT 3
- 是否可以使用不经过训练后的BERTNLU呢 HOT 7
- Why the end-2-end performance mismatch with component level evaluation? 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 convlab-2.