---
license: cc-by-nc-sa-4.0
base_model: InstaDeepAI/nucleotide-transformer-2.5b-multi-species
tags:
- generated_from_trainer
metrics:
- precision
- recall
- accuracy
model-index:
- name: nucleotide-transformer-2.5b-multi-species_ft_BioS45_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-2.5b-multi-species_ft_BioS45_1kbpHG19_DHSs_H3K27AC

This model is a fine-tuned version of [InstaDeepAI/nucleotide-transformer-2.5b-multi-species](https://huggingface.co/InstaDeepAI/nucleotide-transformer-2.5b-multi-species) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7950
- F1 Score: 0.8559
- Precision: 0.8234
- Recall: 0.8911
- Accuracy: 0.8435
- Auc: 0.9171
- Prc: 0.9117

## 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    |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
| 0.5207        | 0.2103 | 500  | 0.4059          | 0.8319   | 0.8038    | 0.8621 | 0.8183   | 0.8975 | 0.8945 |
| 0.429         | 0.4207 | 1000 | 0.4149          | 0.8454   | 0.7824    | 0.9194 | 0.8246   | 0.9137 | 0.9091 |
| 0.4215        | 0.6310 | 1500 | 0.4626          | 0.8318   | 0.7368    | 0.9548 | 0.7985   | 0.9188 | 0.9187 |
| 0.3994        | 0.8414 | 2000 | 0.3757          | 0.8555   | 0.7733    | 0.9573 | 0.8313   | 0.9264 | 0.9226 |
| 0.3733        | 1.0517 | 2500 | 0.4529          | 0.8462   | 0.8658    | 0.8274 | 0.8431   | 0.9240 | 0.9215 |
| 0.3           | 1.2621 | 3000 | 0.5616          | 0.8585   | 0.8464    | 0.8710 | 0.8502   | 0.9248 | 0.9222 |
| 0.3006        | 1.4724 | 3500 | 0.5047          | 0.8498   | 0.8940    | 0.8097 | 0.8507   | 0.9298 | 0.9287 |
| 0.3008        | 1.6828 | 4000 | 0.4289          | 0.8614   | 0.8415    | 0.8823 | 0.8519   | 0.9233 | 0.9218 |
| 0.2882        | 1.8931 | 4500 | 0.4380          | 0.8634   | 0.8323    | 0.8968 | 0.8519   | 0.9263 | 0.9232 |
| 0.2014        | 2.1035 | 5000 | 0.6433          | 0.8624   | 0.8628    | 0.8621 | 0.8565   | 0.9240 | 0.9218 |
| 0.1118        | 2.3138 | 5500 | 0.7087          | 0.8670   | 0.8591    | 0.875  | 0.8599   | 0.9272 | 0.9236 |
| 0.1406        | 2.5242 | 6000 | 0.9509          | 0.8427   | 0.8757    | 0.8121 | 0.8418   | 0.9252 | 0.9212 |
| 0.1304        | 2.7345 | 6500 | 0.7386          | 0.8670   | 0.8398    | 0.8960 | 0.8565   | 0.9265 | 0.9213 |
| 0.1515        | 2.9449 | 7000 | 0.7950          | 0.8559   | 0.8234    | 0.8911 | 0.8435   | 0.9171 | 0.9117 |


### Framework versions

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