---
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_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. -->

# hyenadna-medium-450k-seqlen-hf_ft_BioS45_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: 0.4842
- F1 Score: 0.8087
- Precision: 0.7837
- Recall: 0.8355
- Accuracy: 0.7939
- Auc: 0.8682
- Prc: 0.8657

## 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    |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
| 0.5149        | 0.4205 | 500  | 0.4843          | 0.8028   | 0.7336    | 0.8863 | 0.7728   | 0.8553 | 0.8481 |
| 0.4584        | 0.8410 | 1000 | 0.4805          | 0.8075   | 0.7280    | 0.9065 | 0.7745   | 0.8632 | 0.8518 |
| 0.4489        | 1.2616 | 1500 | 0.4646          | 0.8115   | 0.7566    | 0.875  | 0.7880   | 0.8676 | 0.8583 |
| 0.4367        | 1.6821 | 2000 | 0.4406          | 0.8133   | 0.7810    | 0.8484 | 0.7968   | 0.8720 | 0.8645 |
| 0.4138        | 2.1026 | 2500 | 0.4448          | 0.8189   | 0.7825    | 0.8589 | 0.8019   | 0.8732 | 0.8666 |
| 0.3859        | 2.5231 | 3000 | 0.4459          | 0.8010   | 0.8019    | 0.8    | 0.7926   | 0.8681 | 0.8619 |
| 0.4117        | 2.9437 | 3500 | 0.4532          | 0.8040   | 0.8024    | 0.8056 | 0.7951   | 0.8699 | 0.8678 |
| 0.3722        | 3.3642 | 4000 | 0.4556          | 0.7973   | 0.7969    | 0.7976 | 0.7884   | 0.8665 | 0.8668 |
| 0.3493        | 3.7847 | 4500 | 0.4849          | 0.7944   | 0.8121    | 0.7774 | 0.7901   | 0.8704 | 0.8684 |
| 0.313         | 4.2052 | 5000 | 0.4842          | 0.8087   | 0.7837    | 0.8355 | 0.7939   | 0.8682 | 0.8657 |


### Framework versions

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