---
license: cc-by-nc-sa-4.0
base_model: InstaDeepAI/nucleotide-transformer-500m-human-ref
tags:
- generated_from_trainer
metrics:
- precision
- recall
- accuracy
model-index:
- name: nucleotide-transformer-500m-human-ref_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-human-ref_ft_BioS73_1kbpHG19_DHSs_H3K27AC

This model is a fine-tuned version of [InstaDeepAI/nucleotide-transformer-500m-human-ref](https://huggingface.co/InstaDeepAI/nucleotide-transformer-500m-human-ref) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8150
- F1 Score: 0.8285
- Precision: 0.8557
- Recall: 0.8031
- Accuracy: 0.8226
- Auc: 0.9169
- Prc: 0.9136

## 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  | 0.4571          | 0.8375   | 0.7486    | 0.9504 | 0.8032   | 0.9050 | 0.9000 |
| 0.3951        | 0.3727 | 1000 | 0.4439          | 0.8547   | 0.8010    | 0.9162 | 0.8338   | 0.9132 | 0.9091 |
| 0.4063        | 0.5591 | 1500 | 0.3878          | 0.8530   | 0.8158    | 0.8939 | 0.8356   | 0.9117 | 0.9071 |
| 0.394         | 0.7454 | 2000 | 0.3713          | 0.8551   | 0.7858    | 0.9378 | 0.8304   | 0.9156 | 0.9099 |
| 0.3825        | 0.9318 | 2500 | 0.4021          | 0.8542   | 0.7907    | 0.9288 | 0.8308   | 0.9162 | 0.9117 |
| 0.3348        | 1.1182 | 3000 | 0.6208          | 0.8383   | 0.8677    | 0.8108 | 0.8330   | 0.9181 | 0.9150 |
| 0.2861        | 1.3045 | 3500 | 0.4559          | 0.8629   | 0.8001    | 0.9365 | 0.8412   | 0.9109 | 0.8999 |
| 0.2899        | 1.4909 | 4000 | 0.4412          | 0.8418   | 0.8595    | 0.8247 | 0.8345   | 0.9147 | 0.9063 |
| 0.2739        | 1.6772 | 4500 | 0.5707          | 0.8607   | 0.7903    | 0.9448 | 0.8367   | 0.9168 | 0.9080 |
| 0.3108        | 1.8636 | 5000 | 0.5013          | 0.8642   | 0.8239    | 0.9085 | 0.8476   | 0.9189 | 0.9153 |
| 0.2194        | 2.0499 | 5500 | 0.8897          | 0.8630   | 0.8429    | 0.8841 | 0.8502   | 0.9205 | 0.9139 |
| 0.1629        | 2.2363 | 6000 | 0.9455          | 0.8631   | 0.8307    | 0.8980 | 0.8479   | 0.9162 | 0.9089 |
| 0.1826        | 2.4227 | 6500 | 0.8150          | 0.8285   | 0.8557    | 0.8031 | 0.8226   | 0.9169 | 0.9136 |


### Framework versions

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