---
license: cc-by-nc-sa-4.0
base_model: InstaDeepAI/nucleotide-transformer-500m-1000g
tags:
- generated_from_trainer
metrics:
- precision
- recall
- accuracy
model-index:
- name: nucleotide-transformer-500m-1000g_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-500m-1000g_ft_BioS73_1kbpHG19_DHSs_H3K27AC

This model is a fine-tuned version of [InstaDeepAI/nucleotide-transformer-500m-1000g](https://huggingface.co/InstaDeepAI/nucleotide-transformer-500m-1000g) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7864
- F1 Score: 0.8674
- Precision: 0.8219
- Recall: 0.9183
- Accuracy: 0.8502
- Auc: 0.9181
- Prc: 0.9081

## 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    |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
| 0.4538        | 0.1864 | 500  | 0.5156          | 0.8245   | 0.7173    | 0.9693 | 0.7797   | 0.9012 | 0.8953 |
| 0.4088        | 0.3727 | 1000 | 0.3942          | 0.8517   | 0.8082    | 0.9001 | 0.8327   | 0.9133 | 0.9102 |
| 0.4018        | 0.5591 | 1500 | 0.3782          | 0.8518   | 0.8159    | 0.8911 | 0.8345   | 0.9127 | 0.9086 |
| 0.4043        | 0.7454 | 2000 | 0.3631          | 0.8599   | 0.7934    | 0.9385 | 0.8367   | 0.9176 | 0.9111 |
| 0.3866        | 0.9318 | 2500 | 0.4011          | 0.8586   | 0.7878    | 0.9434 | 0.8341   | 0.9161 | 0.9099 |
| 0.332         | 1.1182 | 3000 | 0.4966          | 0.8603   | 0.8286    | 0.8946 | 0.8449   | 0.9211 | 0.9181 |
| 0.2948        | 1.3045 | 3500 | 0.4844          | 0.8288   | 0.8643    | 0.7961 | 0.8245   | 0.9155 | 0.9026 |
| 0.3062        | 1.4909 | 4000 | 0.4114          | 0.8449   | 0.8675    | 0.8233 | 0.8386   | 0.9223 | 0.9170 |
| 0.2935        | 1.6772 | 4500 | 0.5448          | 0.8767   | 0.8346    | 0.9232 | 0.8613   | 0.9209 | 0.9102 |
| 0.3113        | 1.8636 | 5000 | 0.4740          | 0.8561   | 0.8329    | 0.8806 | 0.8420   | 0.9200 | 0.9152 |
| 0.2362        | 2.0499 | 5500 | 0.8302          | 0.8514   | 0.8544    | 0.8485 | 0.8420   | 0.9222 | 0.9178 |
| 0.1752        | 2.2363 | 6000 | 0.8359          | 0.8681   | 0.8419    | 0.8959 | 0.8546   | 0.9189 | 0.9049 |
| 0.1585        | 2.4227 | 6500 | 0.6381          | 0.8630   | 0.8150    | 0.9169 | 0.8446   | 0.9141 | 0.9058 |
| 0.1535        | 2.6090 | 7000 | 0.7864          | 0.8674   | 0.8219    | 0.9183 | 0.8502   | 0.9181 | 0.9081 |


### Framework versions

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