---
license: bsd-3-clause
base_model: LongSafari/hyenadna-medium-450k-seqlen-hf
tags:
- generated_from_trainer
metrics:
- precision
- recall
- accuracy
model-index:
- name: hyenadna-medium-450k-seqlen-hf_ft_BioS74_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. -->

# hyenadna-medium-450k-seqlen-hf_ft_BioS74_1kbpHG19_DHSs_H3K27AC

This model is a fine-tuned version of [LongSafari/hyenadna-medium-450k-seqlen-hf](https://huggingface.co/LongSafari/hyenadna-medium-450k-seqlen-hf) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4642
- F1 Score: 0.8034
- Precision: 0.7730
- Recall: 0.8363
- Accuracy: 0.7857
- Auc: 0.8626
- Prc: 0.8590

## 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    |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
| 0.5486        | 0.2629 | 500  | 0.5108          | 0.7728   | 0.7601    | 0.7860 | 0.7581   | 0.8210 | 0.8101 |
| 0.4949        | 0.5258 | 1000 | 0.4955          | 0.7852   | 0.7800    | 0.7906 | 0.7736   | 0.8368 | 0.8242 |
| 0.4746        | 0.7886 | 1500 | 0.4766          | 0.7948   | 0.7728    | 0.8182 | 0.7789   | 0.8464 | 0.8356 |
| 0.4782        | 1.0515 | 2000 | 0.4691          | 0.7927   | 0.7933    | 0.7921 | 0.7831   | 0.8544 | 0.8480 |
| 0.4619        | 1.3144 | 2500 | 0.4738          | 0.8016   | 0.7614    | 0.8463 | 0.7807   | 0.8506 | 0.8398 |
| 0.45          | 1.5773 | 3000 | 0.4861          | 0.8063   | 0.7462    | 0.8769 | 0.7794   | 0.8530 | 0.8446 |
| 0.4429        | 1.8402 | 3500 | 0.4836          | 0.7840   | 0.8013    | 0.7675 | 0.7786   | 0.8553 | 0.8508 |
| 0.4459        | 2.1030 | 4000 | 0.4606          | 0.8006   | 0.7833    | 0.8187 | 0.7865   | 0.8616 | 0.8588 |
| 0.413         | 2.3659 | 4500 | 0.4687          | 0.7903   | 0.7931    | 0.7875 | 0.7812   | 0.8600 | 0.8572 |
| 0.4162        | 2.6288 | 5000 | 0.4616          | 0.8036   | 0.7786    | 0.8302 | 0.7875   | 0.8600 | 0.8555 |
| 0.4196        | 2.8917 | 5500 | 0.4642          | 0.8034   | 0.7730    | 0.8363 | 0.7857   | 0.8626 | 0.8590 |


### Framework versions

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