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

# gena-lm-bert-large-t2t_ft_BioS45_1kbpHG19_DHSs_H3K27AC

This model is a fine-tuned version of [AIRI-Institute/gena-lm-bert-large-t2t](https://huggingface.co/AIRI-Institute/gena-lm-bert-large-t2t) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6540
- F1 Score: 0.8311
- Precision: 0.8675
- Recall: 0.7976
- Accuracy: 0.8309
- Auc: 0.9197
- Prc: 0.9139

## 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    |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
| 0.5922        | 0.2103 | 500  | 0.5061          | 0.7627   | 0.8085    | 0.7218 | 0.7657   | 0.8513 | 0.8464 |
| 0.4796        | 0.4207 | 1000 | 0.4288          | 0.8236   | 0.7931    | 0.8565 | 0.8086   | 0.8858 | 0.8800 |
| 0.4414        | 0.6310 | 1500 | 0.4277          | 0.8394   | 0.7999    | 0.8831 | 0.8237   | 0.8978 | 0.8919 |
| 0.4201        | 0.8414 | 2000 | 0.3959          | 0.8537   | 0.8147    | 0.8968 | 0.8397   | 0.9084 | 0.9033 |
| 0.4098        | 1.0517 | 2500 | 0.4331          | 0.8459   | 0.8230    | 0.8702 | 0.8347   | 0.9101 | 0.9052 |
| 0.3969        | 1.2621 | 3000 | 0.4024          | 0.8434   | 0.8531    | 0.8339 | 0.8385   | 0.9155 | 0.9096 |
| 0.3855        | 1.4724 | 3500 | 0.3866          | 0.8600   | 0.8200    | 0.9040 | 0.8464   | 0.9183 | 0.9151 |
| 0.3684        | 1.6828 | 4000 | 0.3759          | 0.8552   | 0.8349    | 0.8766 | 0.8452   | 0.9177 | 0.9138 |
| 0.3692        | 1.8931 | 4500 | 0.3670          | 0.8592   | 0.8096    | 0.9153 | 0.8435   | 0.9218 | 0.9180 |
| 0.3493        | 2.1035 | 5000 | 0.4659          | 0.8646   | 0.8353    | 0.8960 | 0.8536   | 0.9208 | 0.9186 |
| 0.3424        | 2.3138 | 5500 | 0.4562          | 0.8593   | 0.8149    | 0.9089 | 0.8448   | 0.9225 | 0.9176 |
| 0.3307        | 2.5242 | 6000 | 0.4541          | 0.8557   | 0.8066    | 0.9113 | 0.8397   | 0.9230 | 0.9176 |
| 0.3525        | 2.7345 | 6500 | 0.4808          | 0.8565   | 0.8336    | 0.8806 | 0.8460   | 0.9213 | 0.9136 |
| 0.3783        | 2.9449 | 7000 | 0.4244          | 0.8475   | 0.8481    | 0.8468 | 0.8410   | 0.9206 | 0.9089 |
| 0.3226        | 3.1552 | 7500 | 0.6540          | 0.8311   | 0.8675    | 0.7976 | 0.8309   | 0.9197 | 0.9139 |


### Framework versions

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