t5-small-nlu-all-multiwoz21-context3
This model is a fine-tuned version of t5-small on MultiWOZ 2.1 both user and system utterances with context window size == 3.
Refer to ConvLab-3 for model description and usage.
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 128
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 256
- optimizer: Adafactor
- lr_scheduler_type: linear
- num_epochs: 10.0
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0+cu102
- Datasets 2.3.2
- Tokenizers 0.12.1