Edit model card

t5-small-dst-multiwoz21

This model is a fine-tuned version of t5-small 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: 0.001
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 128
  • optimizer: Adafactor
  • lr_scheduler_type: linear
  • num_epochs: 10.0

Framework versions

  • Transformers 4.20.1
  • Pytorch 1.11.0+cu113
  • Datasets 2.3.2
  • Tokenizers 0.12.1
Downloads last month
387

Dataset used to train ConvLab/t5-small-dst-multiwoz21

Evaluation results