metadata
base_model: dmis-lab/biobert-base-cased-v1.2
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: NHS-dmis-binary-512
results: []
NHS-dmis-binary-512
This model is a fine-tuned version of dmis-lab/biobert-base-cased-v1.2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4235
- Accuracy: 0.8125
- Precision: 0.8080
- Recall: 0.8104
- F1: 0.8090
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 |
|---|---|---|---|---|---|---|---|
| 0.0493 | 1.0 | 397 | 0.4334 | 0.8145 | 0.8078 | 0.8140 | 0.8100 |
| 0.0637 | 2.0 | 794 | 0.5025 | 0.7773 | 0.7959 | 0.8004 | 0.7772 |
| 3.1195 | 3.0 | 1191 | 0.5155 | 0.8240 | 0.8176 | 0.8184 | 0.8180 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1