metadata
base_model: dmis-lab/biobert-v1.1
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
model-index:
- name: biobert-base-pubmed-multilabel
results: []
biobert-base-pubmed-multilabel
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: 0.2677
- Precision: 0.9044
- Recall: 0.8528
- F1: 0.8778
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: 5e-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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
|---|---|---|---|---|---|---|
| 0.3373 | 0.2 | 500 | 0.2859 | 0.9093 | 0.8006 | 0.8515 |
| 0.2781 | 0.4 | 1000 | 0.2748 | 0.8972 | 0.8388 | 0.8670 |
| 0.269 | 0.6 | 1500 | 0.2639 | 0.9026 | 0.8405 | 0.8705 |
| 0.2598 | 0.81 | 2000 | 0.2610 | 0.9037 | 0.8435 | 0.8726 |
| 0.2543 | 1.01 | 2500 | 0.2559 | 0.9052 | 0.8494 | 0.8764 |
| 0.2191 | 1.21 | 3000 | 0.2554 | 0.9091 | 0.8437 | 0.8752 |
| 0.2217 | 1.41 | 3500 | 0.2620 | 0.8917 | 0.8676 | 0.8795 |
| 0.2232 | 1.61 | 4000 | 0.2529 | 0.9070 | 0.8470 | 0.8759 |
| 0.2256 | 1.81 | 4500 | 0.2567 | 0.9231 | 0.8176 | 0.8671 |
| 0.2191 | 2.02 | 5000 | 0.2591 | 0.8936 | 0.8731 | 0.8832 |
| 0.1744 | 2.22 | 5500 | 0.2674 | 0.8978 | 0.8631 | 0.8801 |
| 0.1745 | 2.42 | 6000 | 0.2736 | 0.8974 | 0.8566 | 0.8766 |
| 0.1749 | 2.62 | 6500 | 0.2677 | 0.9044 | 0.8528 | 0.8778 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2