---
base_model: zhihan1996/DNABERT-2-117M
tags:
- generated_from_trainer
metrics:
- precision
- recall
- accuracy
model-index:
- name: DNABERT-2-117M_ft_BioS45_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_BioS45_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: 0.7663
- F1 Score: 0.6154
- Precision: 0.8763
- Recall: 0.4742
- Accuracy: 0.6908
- Auc: 0.8534
- Prc: 0.8406

## 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    |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
| 0.7033        | 0.4205 | 500  | 0.5780          | 0.7163   | 0.7317    | 0.7016 | 0.7101   | 0.7860 | 0.7818 |
| 0.5929        | 0.8410 | 1000 | 0.5370          | 0.7339   | 0.7525    | 0.7161 | 0.7291   | 0.8066 | 0.7979 |
| 0.5608        | 1.2616 | 1500 | 0.5352          | 0.7532   | 0.7508    | 0.7556 | 0.7417   | 0.8204 | 0.8097 |
| 0.5471        | 1.6821 | 2000 | 0.5455          | 0.6955   | 0.8211    | 0.6032 | 0.7244   | 0.8317 | 0.8200 |
| 0.5252        | 2.1026 | 2500 | 0.5145          | 0.7897   | 0.7367    | 0.8508 | 0.7636   | 0.8384 | 0.8261 |
| 0.4833        | 2.5231 | 3000 | 0.5229          | 0.7976   | 0.7146    | 0.9024 | 0.7610   | 0.8469 | 0.8351 |
| 0.5161        | 2.9437 | 3500 | 0.4988          | 0.7593   | 0.8049    | 0.7185 | 0.7623   | 0.8506 | 0.8393 |
| 0.4921        | 3.3642 | 4000 | 0.4784          | 0.7967   | 0.7447    | 0.8565 | 0.7720   | 0.8541 | 0.8426 |
| 0.4779        | 3.7847 | 4500 | 0.7663          | 0.6154   | 0.8763    | 0.4742 | 0.6908   | 0.8534 | 0.8406 |


### Framework versions

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