---
license: cc-by-nc-sa-4.0
base_model: InstaDeepAI/nucleotide-transformer-v2-50m-multi-species
tags:
- generated_from_trainer
metrics:
- precision
- recall
- accuracy
model-index:
- name: nucleotide-transformer-v2-50m-multi-species_ft_BioS73_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-v2-50m-multi-species_ft_BioS73_1kbpHG19_DHSs_H3K27AC

This model is a fine-tuned version of [InstaDeepAI/nucleotide-transformer-v2-50m-multi-species](https://huggingface.co/InstaDeepAI/nucleotide-transformer-v2-50m-multi-species) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5982
- F1 Score: 0.8659
- Precision: 0.8638
- Recall: 0.8680
- Accuracy: 0.8565
- Auc: 0.9221
- Prc: 0.9108

## 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    |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
| 0.4842        | 0.1864 | 500  | 0.4405          | 0.8399   | 0.7690    | 0.9253 | 0.8118   | 0.8896 | 0.8855 |
| 0.3895        | 0.3727 | 1000 | 0.3708          | 0.8565   | 0.8186    | 0.8980 | 0.8394   | 0.9145 | 0.9127 |
| 0.3812        | 0.5591 | 1500 | 0.3732          | 0.8650   | 0.8468    | 0.8841 | 0.8528   | 0.9200 | 0.9179 |
| 0.3785        | 0.7454 | 2000 | 0.3683          | 0.8681   | 0.8566    | 0.8799 | 0.8572   | 0.9226 | 0.9183 |
| 0.352         | 0.9318 | 2500 | 0.3957          | 0.8678   | 0.8312    | 0.9078 | 0.8524   | 0.9233 | 0.9208 |
| 0.3234        | 1.1182 | 3000 | 0.4323          | 0.8701   | 0.8222    | 0.9239 | 0.8528   | 0.9261 | 0.9220 |
| 0.2959        | 1.3045 | 3500 | 0.3964          | 0.8749   | 0.8237    | 0.9330 | 0.8576   | 0.9231 | 0.9151 |
| 0.3007        | 1.4909 | 4000 | 0.3848          | 0.8715   | 0.8514    | 0.8925 | 0.8595   | 0.9247 | 0.9188 |
| 0.3001        | 1.6772 | 4500 | 0.4423          | 0.8790   | 0.8411    | 0.9204 | 0.8647   | 0.9227 | 0.9129 |
| 0.3094        | 1.8636 | 5000 | 0.3997          | 0.8737   | 0.8525    | 0.8959 | 0.8617   | 0.9288 | 0.9235 |
| 0.2533        | 2.0499 | 5500 | 0.5849          | 0.8611   | 0.8719    | 0.8506 | 0.8535   | 0.9290 | 0.9247 |
| 0.2049        | 2.2363 | 6000 | 0.5982          | 0.8659   | 0.8638    | 0.8680 | 0.8565   | 0.9221 | 0.9108 |


### Framework versions

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