ClinicalT5-base-finetuned-biomedical
This model is a fine-tuned version of luqh/ClinicalT5-base on the sem_eval_2024_task_2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2017
- Rouge1: 51.0
- Rouge2: 0.0
- Rougel: 51.0
- Rougelsum: 51.0
- Gen Len: 3.71
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 425 | 0.2227 | 49.5 | 0.0 | 49.5 | 49.5 | 3.015 |
| 1.7568 | 2.0 | 850 | 0.2053 | 49.0 | 0.0 | 49.0 | 49.0 | 3.09 |
| 0.227 | 3.0 | 1275 | 0.2012 | 51.0 | 0.0 | 51.0 | 51.0 | 3.24 |
| 0.2186 | 4.0 | 1700 | 0.2011 | 52.0 | 0.0 | 52.0 | 52.0 | 3.29 |
| 0.2173 | 5.0 | 2125 | 0.2017 | 51.0 | 0.0 | 51.0 | 51.0 | 3.71 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 43
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for Shijia/ClinicalT5-base-finetuned-biomedical
Base model
luqh/ClinicalT5-baseEvaluation results
- Rouge1 on sem_eval_2024_task_2validation set self-reported51.000