|
--- |
|
license: cc0-1.0 |
|
base_model: bionlp/bluebert_pubmed_uncased_L-12_H-768_A-12 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: NHS-bluebert-multi |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# NHS-bluebert-multi |
|
|
|
This model is a fine-tuned version of [bionlp/bluebert_pubmed_uncased_L-12_H-768_A-12](https://huggingface.co/bionlp/bluebert_pubmed_uncased_L-12_H-768_A-12) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8729 |
|
- Accuracy: 0.7098 |
|
- Precision: 0.7153 |
|
- Recall: 0.7098 |
|
- F1: 0.7118 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
| 0.1093 | 1.0 | 397 | 0.7138 | 0.7243 | 0.7288 | 0.7243 | 0.7262 | |
|
| 0.0518 | 2.0 | 794 | 0.8117 | 0.7073 | 0.7007 | 0.7073 | 0.6926 | |
|
| 1.9889 | 3.0 | 1191 | 0.8729 | 0.7098 | 0.7153 | 0.7098 | 0.7118 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
