metadata
base_model: dmis-lab/biobert-v1.1
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: biobert-finetuned-ner1
results: []
biobert-finetuned-ner1
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: 0.6653
- Precision: 0.6417
- Recall: 0.6985
- F1: 0.6689
- Accuracy: 0.8611
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 | 0.4133 | 0.6172 | 0.6674 | 0.6413 | 0.8529 |
| 0.4433 | 2.0 | 610 | 0.4058 | 0.6121 | 0.6868 | 0.6473 | 0.8568 |
| 0.4433 | 3.0 | 915 | 0.4456 | 0.6323 | 0.7015 | 0.6651 | 0.8594 |
| 0.2431 | 4.0 | 1220 | 0.4708 | 0.6323 | 0.6925 | 0.6610 | 0.8612 |
| 0.1563 | 5.0 | 1525 | 0.5084 | 0.6434 | 0.6998 | 0.6704 | 0.8652 |
| 0.1563 | 6.0 | 1830 | 0.5655 | 0.6438 | 0.6801 | 0.6615 | 0.8607 |
| 0.1038 | 7.0 | 2135 | 0.6173 | 0.6385 | 0.6918 | 0.6641 | 0.8591 |
| 0.1038 | 8.0 | 2440 | 0.6352 | 0.6410 | 0.7011 | 0.6697 | 0.8608 |
| 0.0754 | 9.0 | 2745 | 0.6600 | 0.6406 | 0.6951 | 0.6668 | 0.8609 |
| 0.0599 | 10.0 | 3050 | 0.6653 | 0.6417 | 0.6985 | 0.6689 | 0.8611 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1