Downloads · 30 days
0
ddpt-policy-multiwoz21
ConvLab/ddpt-policy-multiwoz21
ddpt-policy-multiwoz21 is a machine learning model from ConvLab. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This is a DDPT model (https://aclanthology.org/2022.coling-1.21/) trained on MultiWOZ 2.1
Access
Public
Updated Dec 21, 2022
Repo size
9.3 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.mdl9.3 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Dec 21, 2022
- Updated
- Dec 21, 2022
- SHA
- 2285042a
Datasets
Model card
From the Hugging Face model README
ddpt-policy-sgd
This is a DDPT model (https://aclanthology.org/2022.coling-1.21/) trained on MultiWOZ 2.1
Refer to ConvLab-3 for model description and usage.
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 64
- seed: 1
- optimizer: Adam
- num_epochs: 40
- use checkpoint which performed best on validation set
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.2+cu111
- License
- apache-2.0
- Languages
- en
- Created
- Dec 21, 2022
- Updated
- Dec 21, 2022