clinical-t5

This is a finetuned T5-small model from Google, a checkpoint with 60 million parameters, for clinical note summarization. It was finetuned with the augmented-clinical-notes dataset, available in the Hugging Face.

Intended uses & limitations

The model was created for learning purposes. Hence, although being briefly evaluated in this notebook, it should be further refined.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4

Framework versions

• Transformers 4.30.0
• Pytorch 2.2.1+cu121
• Datasets 2.19.1
• Tokenizers 0.13.3