metadata
language:
- en
license: apache-2.0
tags:
- roberta
- classification
- dialog state tracking
- conversational system
- task-oriented dialog
datasets:
- ConvLab/sgd
metrics:
- Joint Goal Accuracy
- Slot F1
model-index:
- name: setsumbt-dst-sgd
results:
- task:
type: classification
name: dialog state tracking
dataset:
type: ConvLab/sgd
name: SGD
split: test
metrics:
- type: Joint Goal Accuracy
value: 20
name: JGA
- type: Slot F1
value: 58.8
name: Slot F1
SetSUMBT-dst-sgd
This model is a fine-tuned version SetSUMBT of roberta-base on Schema-Guided Dialog.
Refer to ConvLab-3 for model description and usage.
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.00001
- train_batch_size: 3
- eval_batch_size: 16
- seed: 0
- gradient_accumulation_steps: 1
- optimizer: AdamW
- lr_scheduler_type: linear
- num_epochs: 50.0
Framework versions
- Transformers 4.17.0
- Pytorch 1.8.0+cu110
- Datasets 2.3.2
- Tokenizers 0.12.1