---
license: bsd-3-clause
base_model: LongSafari/hyenadna-large-1m-seqlen-hf
tags:
- generated_from_trainer
metrics:
- precision
- recall
- accuracy
model-index:
- name: hyenadna-large-1m-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-large-1m-seqlen-hf_ft_BioS74_1kbpHG19_DHSs_H3K27AC

This model is a fine-tuned version of [LongSafari/hyenadna-large-1m-seqlen-hf](https://huggingface.co/LongSafari/hyenadna-large-1m-seqlen-hf) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4843
- F1 Score: 0.7964
- Precision: 0.7556
- Recall: 0.8418
- Accuracy: 0.7747
- Auc: 0.8453
- Prc: 0.8347

## 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: 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: 20
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | F1 Score | Precision | Recall | Accuracy | Auc    | Prc    |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
| 0.5422        | 0.1314 | 500  | 0.5443          | 0.7378   | 0.7886    | 0.6931 | 0.7420   | 0.8185 | 0.8068 |
| 0.5205        | 0.2629 | 1000 | 0.5236          | 0.7618   | 0.7807    | 0.7438 | 0.7565   | 0.8309 | 0.8226 |
| 0.5233        | 0.3943 | 1500 | 0.5168          | 0.7576   | 0.7893    | 0.7283 | 0.7560   | 0.8319 | 0.8199 |
| 0.5023        | 0.5258 | 2000 | 0.5105          | 0.7933   | 0.7591    | 0.8307 | 0.7733   | 0.8369 | 0.8254 |
| 0.4879        | 0.6572 | 2500 | 0.5088          | 0.7988   | 0.7263    | 0.8875 | 0.7660   | 0.8382 | 0.8229 |
| 0.5064        | 0.7886 | 3000 | 0.4937          | 0.7919   | 0.7569    | 0.8302 | 0.7715   | 0.8373 | 0.8267 |
| 0.4934        | 0.9201 | 3500 | 0.4923          | 0.7971   | 0.7661    | 0.8307 | 0.7786   | 0.8452 | 0.8289 |
| 0.4952        | 1.0515 | 4000 | 0.4834          | 0.7809   | 0.7915    | 0.7705 | 0.7736   | 0.8480 | 0.8352 |
| 0.488         | 1.1830 | 4500 | 0.4898          | 0.7899   | 0.7575    | 0.8252 | 0.7702   | 0.8404 | 0.8293 |
| 0.494         | 1.3144 | 5000 | 0.4843          | 0.7964   | 0.7556    | 0.8418 | 0.7747   | 0.8453 | 0.8347 |


### Framework versions

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