| # gpt2-medium-nlg-multiwoz21 | |
| This model is a fine-tuned version of [GPT2-medium](https://huggingface.co/gpt2-medium) on [MultiWOZ21](https://huggingface.co/datasets/ConvLab/multiwoz21). | |
| Refer to [ConvLab-3](https://github.com/ConvLab/ConvLab-3) for model description and usage. | |
| ## Training procedure | |
| ### Training hyperparameters | |
| The following hyperparameters were used during training: | |
| - learning_rate: 5e-5 | |
| - train_batch_size: 64 | |
| - gradient_accumulation_steps: 2 | |
| - total_train_batch_size: 128 | |
| - optimizer: AdamW | |
| - lr_scheduler_type: linear | |
| - num_epochs: 20 | |
| ### Framework versions | |
| - Transformers 4.23.1 | |
| - Pytorch 1.10.1+cu111 | |