metadata
base_model: dmis-lab/biobert-v1.1
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: biobert-all-deep
results: []
biobert-all-deep
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: 0.8095
- Precision: 0.6591
- Recall: 0.7116
- F1: 0.6843
- Accuracy: 0.8236
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 | 363 | 0.5639 | 0.5973 | 0.6865 | 0.6388 | 0.8149 |
| 0.6983 | 2.0 | 726 | 0.5410 | 0.6263 | 0.7052 | 0.6634 | 0.8238 |
| 0.3859 | 3.0 | 1089 | 0.5557 | 0.6544 | 0.7011 | 0.6769 | 0.8245 |
| 0.3859 | 4.0 | 1452 | 0.5803 | 0.6579 | 0.7064 | 0.6813 | 0.8276 |
| 0.276 | 5.0 | 1815 | 0.6461 | 0.6598 | 0.7105 | 0.6842 | 0.8238 |
| 0.1944 | 6.0 | 2178 | 0.6995 | 0.6616 | 0.7120 | 0.6859 | 0.8237 |
| 0.1505 | 7.0 | 2541 | 0.7337 | 0.6563 | 0.7195 | 0.6865 | 0.8253 |
| 0.1505 | 8.0 | 2904 | 0.7710 | 0.6664 | 0.7120 | 0.6884 | 0.8255 |
| 0.1178 | 9.0 | 3267 | 0.8030 | 0.6541 | 0.7165 | 0.6838 | 0.8233 |
| 0.1006 | 10.0 | 3630 | 0.8095 | 0.6591 | 0.7116 | 0.6843 | 0.8236 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1