metadata
base_model: dmis-lab/biobert-v1.1
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: biobert-finetuned-ner
results: []
biobert-finetuned-ner
This model is a fine-tuned version of dmis-lab/biobert-v1.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6965
- Precision: 0.6381
- Recall: 0.6865
- F1: 0.6614
- Accuracy: 0.8583
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 305 | 0.4123 | 0.6110 | 0.6694 | 0.6389 | 0.8542 |
| 0.4534 | 2.0 | 610 | 0.4023 | 0.6259 | 0.6848 | 0.6540 | 0.8586 |
| 0.4534 | 3.0 | 915 | 0.4384 | 0.6369 | 0.6991 | 0.6666 | 0.8615 |
| 0.2438 | 4.0 | 1220 | 0.4799 | 0.6445 | 0.6941 | 0.6684 | 0.8615 |
| 0.1551 | 5.0 | 1525 | 0.5190 | 0.6464 | 0.6908 | 0.6678 | 0.8628 |
| 0.1551 | 6.0 | 1830 | 0.5772 | 0.6454 | 0.6751 | 0.6599 | 0.8597 |
| 0.1044 | 7.0 | 2135 | 0.6141 | 0.6413 | 0.6881 | 0.6639 | 0.8586 |
| 0.1044 | 8.0 | 2440 | 0.6587 | 0.6353 | 0.6945 | 0.6636 | 0.8590 |
| 0.0755 | 9.0 | 2745 | 0.6856 | 0.6357 | 0.6905 | 0.6620 | 0.8580 |
| 0.0604 | 10.0 | 3050 | 0.6965 | 0.6381 | 0.6865 | 0.6614 | 0.8583 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1