<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
biomedical_question_answering
This model is a fine-tuned version of microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext on a custom dataset of question answer pairs annotated from research papers from Pubmed. It achieves the following results on the evaluation set:
- Loss: 2.6629
Model description
Model finetuned on PubmedBERT using custom daatset
Intended uses & limitations
For question answering related to biomedical research papers.
Training and evaluation data
Data https://huggingface.co/datasets/Shushant/BiomedicalQuestionAnsweringDataset
Training procedure
Finetuning using Trainer API
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 236 | 1.6866 |
| No log | 2.0 | 472 | 1.5432 |
| 0.737 | 3.0 | 708 | 1.7998 |
| 0.737 | 4.0 | 944 | 1.9746 |
| 0.2893 | 5.0 | 1180 | 1.9510 |
| 0.2893 | 6.0 | 1416 | 2.1479 |
| 0.1562 | 7.0 | 1652 | 2.3304 |
| 0.1562 | 8.0 | 1888 | 2.5882 |
| 0.0823 | 9.0 | 2124 | 2.6494 |
| 0.0823 | 10.0 | 2360 | 2.6629 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
