---
license: cc-by-nc-sa-4.0
base_model: InstaDeepAI/nucleotide-transformer-v2-250m-multi-species
tags:
- generated_from_trainer
metrics:
- precision
- recall
- accuracy
model-index:
- name: nucleotide-transformer-v2-250m-multi-species_ft_BioS2_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. -->

# nucleotide-transformer-v2-250m-multi-species_ft_BioS2_1kbpHG19_DHSs_H3K27AC

This model is a fine-tuned version of [InstaDeepAI/nucleotide-transformer-v2-250m-multi-species](https://huggingface.co/InstaDeepAI/nucleotide-transformer-v2-250m-multi-species) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4669
- F1 Score: 0.8482
- Precision: 0.9254
- Recall: 0.7829
- Accuracy: 0.8514
- Auc: 0.9436
- Prc: 0.9461

## 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    |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
| 0.5459        | 0.0840 | 500  | 0.4629          | 0.8082   | 0.7697    | 0.8507 | 0.7858   | 0.8605 | 0.8526 |
| 0.476         | 0.1681 | 1000 | 0.4365          | 0.8113   | 0.8419    | 0.7829 | 0.8068   | 0.8914 | 0.8847 |
| 0.4251        | 0.2521 | 1500 | 0.4039          | 0.8445   | 0.7750    | 0.9277 | 0.8188   | 0.9021 | 0.8959 |
| 0.4355        | 0.3362 | 2000 | 0.4217          | 0.8192   | 0.8716    | 0.7727 | 0.8191   | 0.9104 | 0.9059 |
| 0.4098        | 0.4202 | 2500 | 0.3846          | 0.8278   | 0.8977    | 0.7680 | 0.8305   | 0.9216 | 0.9202 |
| 0.3904        | 0.5043 | 3000 | 0.3587          | 0.8477   | 0.8689    | 0.8276 | 0.8423   | 0.9239 | 0.9266 |
| 0.3785        | 0.5883 | 3500 | 0.3705          | 0.8592   | 0.7885    | 0.9439 | 0.8359   | 0.9306 | 0.9291 |
| 0.37          | 0.6724 | 4000 | 0.3494          | 0.8648   | 0.8831    | 0.8472 | 0.8594   | 0.9353 | 0.9370 |
| 0.3692        | 0.7564 | 4500 | 0.3426          | 0.8667   | 0.8688    | 0.8647 | 0.8589   | 0.9363 | 0.9377 |
| 0.3528        | 0.8405 | 5000 | 0.3328          | 0.8756   | 0.8447    | 0.9087 | 0.8630   | 0.9397 | 0.9405 |
| 0.3494        | 0.9245 | 5500 | 0.3519          | 0.8750   | 0.8640    | 0.8862 | 0.8657   | 0.9403 | 0.9428 |
| 0.3383        | 1.0086 | 6000 | 0.3942          | 0.8734   | 0.8074    | 0.9512 | 0.8537   | 0.9451 | 0.9472 |
| 0.2873        | 1.0926 | 6500 | 0.3763          | 0.8873   | 0.8707    | 0.9046 | 0.8781   | 0.9463 | 0.9481 |
| 0.2825        | 1.1767 | 7000 | 0.3689          | 0.8831   | 0.8293    | 0.9442 | 0.8674   | 0.9455 | 0.9461 |
| 0.2906        | 1.2607 | 7500 | 0.3785          | 0.8851   | 0.8664    | 0.9046 | 0.8754   | 0.9453 | 0.9469 |
| 0.2796        | 1.3448 | 8000 | 0.4669          | 0.8482   | 0.9254    | 0.7829 | 0.8514   | 0.9436 | 0.9461 |


### Framework versions

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