---
base_model: AIRI-Institute/gena-lm-bert-base-t2t
tags:
- generated_from_trainer
metrics:
- precision
- recall
- accuracy
model-index:
- name: gena-lm-bert-base-t2t_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. -->

# gena-lm-bert-base-t2t_ft_BioS74_1kbpHG19_DHSs_H3K27AC

This model is a fine-tuned version of [AIRI-Institute/gena-lm-bert-base-t2t](https://huggingface.co/AIRI-Institute/gena-lm-bert-base-t2t) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4989
- F1 Score: 0.8378
- Precision: 0.8054
- Recall: 0.8729
- Accuracy: 0.8230
- Auc: 0.8768
- Prc: 0.8333

## 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    |
|:-------------:|:------:|:-----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
| 0.6857        | 0.1314 | 500   | 0.6358          | 0.7270   | 0.7424    | 0.7122 | 0.7200   | 0.7586 | 0.7471 |
| 0.6115        | 0.2629 | 1000  | 0.5765          | 0.7146   | 0.7998    | 0.6459 | 0.7300   | 0.7812 | 0.7800 |
| 0.5477        | 0.3943 | 1500  | 0.4954          | 0.8091   | 0.7478    | 0.8815 | 0.7823   | 0.8401 | 0.8126 |
| 0.487         | 0.5258 | 2000  | 0.4893          | 0.8185   | 0.7659    | 0.8790 | 0.7960   | 0.8423 | 0.7918 |
| 0.4824        | 0.6572 | 2500  | 0.5362          | 0.8176   | 0.7241    | 0.9387 | 0.7807   | 0.8192 | 0.7493 |
| 0.5023        | 0.7886 | 3000  | 0.4826          | 0.8279   | 0.7491    | 0.9252 | 0.7986   | 0.8656 | 0.8357 |
| 0.4762        | 0.9201 | 3500  | 0.4686          | 0.8229   | 0.7869    | 0.8624 | 0.8057   | 0.8765 | 0.8499 |
| 0.4796        | 1.0515 | 4000  | 0.4538          | 0.8201   | 0.7977    | 0.8438 | 0.8062   | 0.8835 | 0.8673 |
| 0.4654        | 1.1830 | 4500  | 0.4534          | 0.8285   | 0.7531    | 0.9206 | 0.8004   | 0.8641 | 0.8296 |
| 0.4583        | 1.3144 | 5000  | 0.4943          | 0.8285   | 0.7376    | 0.9448 | 0.7952   | 0.8512 | 0.7967 |
| 0.4605        | 1.4458 | 5500  | 0.4470          | 0.8308   | 0.8040    | 0.8594 | 0.8167   | 0.8903 | 0.8718 |
| 0.4316        | 1.5773 | 6000  | 0.4880          | 0.8338   | 0.7886    | 0.8845 | 0.8154   | 0.8626 | 0.8079 |
| 0.4447        | 1.7087 | 6500  | 0.4371          | 0.8369   | 0.7814    | 0.9011 | 0.8162   | 0.8866 | 0.8626 |
| 0.4355        | 1.8402 | 7000  | 0.4654          | 0.8273   | 0.8032    | 0.8528 | 0.8136   | 0.8713 | 0.8183 |
| 0.4447        | 1.9716 | 7500  | 0.4687          | 0.8327   | 0.7729    | 0.9026 | 0.8101   | 0.8877 | 0.8643 |
| 0.4238        | 2.1030 | 8000  | 0.4868          | 0.8350   | 0.7753    | 0.9046 | 0.8128   | 0.8889 | 0.8651 |
| 0.439         | 2.2345 | 8500  | 0.4307          | 0.8329   | 0.8271    | 0.8388 | 0.8238   | 0.8997 | 0.8889 |
| 0.4248        | 2.3659 | 9000  | 0.4533          | 0.8408   | 0.7991    | 0.8870 | 0.8241   | 0.8902 | 0.8637 |
| 0.4175        | 2.4974 | 9500  | 0.5197          | 0.8376   | 0.7963    | 0.8835 | 0.8207   | 0.8802 | 0.8442 |
| 0.4426        | 2.6288 | 10000 | 0.4643          | 0.8246   | 0.8311    | 0.8182 | 0.8178   | 0.8974 | 0.8796 |
| 0.4538        | 2.7603 | 10500 | 0.5072          | 0.8345   | 0.8211    | 0.8483 | 0.8238   | 0.8717 | 0.8182 |
| 0.4105        | 2.8917 | 11000 | 0.5272          | 0.8360   | 0.8085    | 0.8654 | 0.8222   | 0.8812 | 0.8447 |
| 0.4234        | 3.0231 | 11500 | 0.4989          | 0.8378   | 0.8054    | 0.8729 | 0.8230   | 0.8768 | 0.8333 |


### Framework versions

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