BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext-finetuned-ade-v2-classification
This model is a fine-tuned version of BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext on the ade_corpus_v2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1982
- Accuracy: 0.9611
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: 1.8069489920382708e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 10
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.1657 | 1.0 | 1176 | 0.1405 | 0.9511 |
0.1019 | 2.0 | 2352 | 0.1767 | 0.9575 |
0.055 | 3.0 | 3528 | 0.1982 | 0.9611 |
0.0424 | 4.0 | 4704 | 0.2038 | 0.9605 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2
- Downloads last month
- 7
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.