metadata
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: []
NHS-bluebert-multi
This model is a fine-tuned version of 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