Commit
·
f330634
1
Parent(s):
942d185
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,32 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- dialogue policy
|
| 7 |
+
- task-oriented dialog
|
| 8 |
+
datasets:
|
| 9 |
+
- ConvLab/multiwoz21
|
| 10 |
+
|
| 11 |
---
|
| 12 |
+
|
| 13 |
+
# ddpt-policy-sgd
|
| 14 |
+
|
| 15 |
+
This is a DDPT model (https://aclanthology.org/2022.coling-1.21/) trained on [MultiWOZ 2.1](https://huggingface.co/datasets/ConvLab/multiwoz21)
|
| 16 |
+
|
| 17 |
+
Refer to [ConvLab-3](https://github.com/ConvLab/ConvLab-3) for model description and usage.
|
| 18 |
+
|
| 19 |
+
## Training procedure
|
| 20 |
+
|
| 21 |
+
### Training hyperparameters
|
| 22 |
+
|
| 23 |
+
The following hyperparameters were used during training:
|
| 24 |
+
- learning_rate: 1e-05
|
| 25 |
+
- train_batch_size: 64
|
| 26 |
+
- seed: 0
|
| 27 |
+
- optimizer: Adam
|
| 28 |
+
- num_epochs: 40
|
| 29 |
+
- use checkpoint which performed best on validation set
|
| 30 |
+
### Framework versions
|
| 31 |
+
- Transformers 4.18.0
|
| 32 |
+
- Pytorch 1.10.2+cu111
|