---
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_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. -->

# nucleotide-transformer-v2-50m-multi-species_ft_BioS74_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: 0.4277
- F1 Score: 0.8355
- Precision: 0.8318
- Recall: 0.8393
- Accuracy: 0.8270
- Auc: 0.9066
- Prc: 0.9000

## 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    |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
| 0.5314        | 0.1314 | 500  | 0.4688          | 0.8060   | 0.7652    | 0.8513 | 0.7854   | 0.8552 | 0.8400 |
| 0.4807        | 0.2629 | 1000 | 0.4967          | 0.7824   | 0.8433    | 0.7298 | 0.7875   | 0.8783 | 0.8671 |
| 0.4541        | 0.3943 | 1500 | 0.4272          | 0.8177   | 0.8166    | 0.8187 | 0.8088   | 0.8900 | 0.8819 |
| 0.4213        | 0.5258 | 2000 | 0.4602          | 0.8361   | 0.7841    | 0.8955 | 0.8162   | 0.8916 | 0.8819 |
| 0.4085        | 0.6572 | 2500 | 0.4336          | 0.8363   | 0.7528    | 0.9407 | 0.8073   | 0.8959 | 0.8890 |
| 0.4383        | 0.7886 | 3000 | 0.4106          | 0.8240   | 0.8238    | 0.8242 | 0.8157   | 0.8978 | 0.8913 |
| 0.4237        | 0.9201 | 3500 | 0.4270          | 0.8372   | 0.8043    | 0.8729 | 0.8222   | 0.9017 | 0.8957 |
| 0.4121        | 1.0515 | 4000 | 0.4787          | 0.7913   | 0.8662    | 0.7283 | 0.7988   | 0.9028 | 0.8948 |
| 0.3789        | 1.1830 | 4500 | 0.4081          | 0.8379   | 0.8139    | 0.8634 | 0.8251   | 0.8999 | 0.8889 |
| 0.3736        | 1.3144 | 5000 | 0.4348          | 0.8344   | 0.8167    | 0.8528 | 0.8228   | 0.9020 | 0.8951 |
| 0.3655        | 1.4458 | 5500 | 0.4388          | 0.8153   | 0.8509    | 0.7825 | 0.8144   | 0.9056 | 0.8995 |
| 0.3597        | 1.5773 | 6000 | 0.4277          | 0.8355   | 0.8318    | 0.8393 | 0.8270   | 0.9066 | 0.9000 |


### Framework versions

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