metadata
license: mit
base_model: microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: NHS-pubmedbert-multi
results: []
NHS-pubmedbert-multi
This model is a fine-tuned version of microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8814
- Accuracy: 0.7148
- Precision: 0.7181
- Recall: 0.7148
- F1: 0.7151
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: 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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.0855 | 1.0 | 397 | 0.7355 | 0.7192 | 0.7254 | 0.7192 | 0.7212 |
| 0.0541 | 2.0 | 794 | 0.7926 | 0.7180 | 0.7181 | 0.7180 | 0.7036 |
| 0.2545 | 3.0 | 1191 | 0.8814 | 0.7148 | 0.7181 | 0.7148 | 0.7151 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2