---
base_model: zhihan1996/DNABERT-2-117M
tags:
- generated_from_trainer
metrics:
- precision
- recall
- accuracy
model-index:
- name: DNABERT-2-117M_ft_BioS73_1kbpHG19_DHSs_H3K27AC
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# DNABERT-2-117M_ft_BioS73_1kbpHG19_DHSs_H3K27AC

This model is a fine-tuned version of [zhihan1996/DNABERT-2-117M](https://huggingface.co/zhihan1996/DNABERT-2-117M) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4847
- F1 Score: 0.8003
- Precision: 0.8578
- Recall: 0.75
- Accuracy: 0.8002
- Auc: 0.8937
- Prc: 0.8857

## 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: 1e-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: 20
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | F1 Score | Precision | Recall | Accuracy | Auc    | Prc    |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
| 0.6224        | 0.3726 | 500  | 0.7088          | 0.7453   | 0.5976    | 0.9902 | 0.6388   | 0.8483 | 0.8530 |
| 0.5527        | 0.7452 | 1000 | 0.4761          | 0.8021   | 0.7657    | 0.8422 | 0.7782   | 0.8540 | 0.8575 |
| 0.5232        | 1.1177 | 1500 | 0.4819          | 0.7961   | 0.8003    | 0.7919 | 0.7835   | 0.8598 | 0.8622 |
| 0.5198        | 1.4903 | 2000 | 0.4690          | 0.8087   | 0.7914    | 0.8268 | 0.7913   | 0.8641 | 0.8664 |
| 0.5012        | 1.8629 | 2500 | 0.4830          | 0.7676   | 0.8429    | 0.7046 | 0.7723   | 0.8693 | 0.8699 |
| 0.4683        | 2.2355 | 3000 | 0.4665          | 0.8259   | 0.7532    | 0.9141 | 0.7943   | 0.8768 | 0.8756 |
| 0.4689        | 2.6080 | 3500 | 0.4254          | 0.8285   | 0.7695    | 0.8973 | 0.8017   | 0.8845 | 0.8808 |
| 0.435         | 2.9806 | 4000 | 0.4477          | 0.8340   | 0.7540    | 0.9330 | 0.8017   | 0.8893 | 0.8834 |
| 0.4208        | 3.3532 | 4500 | 0.4703          | 0.8134   | 0.8368    | 0.7912 | 0.8062   | 0.8892 | 0.8829 |
| 0.4145        | 3.7258 | 5000 | 0.5007          | 0.7988   | 0.8421    | 0.7598 | 0.7958   | 0.8921 | 0.8850 |
| 0.4031        | 4.0984 | 5500 | 0.4230          | 0.8363   | 0.7945    | 0.8827 | 0.8155   | 0.8921 | 0.8844 |
| 0.3825        | 4.4709 | 6000 | 0.4299          | 0.8397   | 0.7611    | 0.9365 | 0.8092   | 0.8936 | 0.8853 |
| 0.3875        | 4.8435 | 6500 | 0.5066          | 0.7971   | 0.8664    | 0.7381 | 0.7995   | 0.8946 | 0.8871 |
| 0.3771        | 5.2161 | 7000 | 0.6022          | 0.7480   | 0.8870    | 0.6466 | 0.7674   | 0.8949 | 0.8869 |
| 0.363         | 5.5887 | 7500 | 0.4847          | 0.8003   | 0.8578    | 0.75   | 0.8002   | 0.8937 | 0.8857 |


### Framework versions

- Transformers 4.42.3
- Pytorch 2.3.0+cu121
- Datasets 2.18.0
- Tokenizers 0.19.0