---
base_model: AIRI-Institute/gena-lm-bert-base-t2t-multi
tags:
- generated_from_trainer
metrics:
- precision
- recall
- accuracy
model-index:
- name: gena-lm-bert-base-t2t-multi_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-base-t2t-multi_ft_BioS45_1kbpHG19_DHSs_H3K27AC

This model is a fine-tuned version of [AIRI-Institute/gena-lm-bert-base-t2t-multi](https://huggingface.co/AIRI-Institute/gena-lm-bert-base-t2t-multi) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4693
- F1 Score: 0.8489
- Precision: 0.8151
- Recall: 0.8855
- Accuracy: 0.8355
- Auc: 0.8880
- Prc: 0.8543

## 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    |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
| 0.7045        | 0.2103 | 500  | 0.6716          | 0.3608   | 0.8731    | 0.2274 | 0.5797   | 0.7448 | 0.7630 |
| 0.6504        | 0.4207 | 1000 | 0.6005          | 0.7373   | 0.7184    | 0.7573 | 0.7186   | 0.7845 | 0.7959 |
| 0.5759        | 0.6310 | 1500 | 0.5370          | 0.7482   | 0.7872    | 0.7129 | 0.7497   | 0.7960 | 0.7969 |
| 0.5182        | 0.8414 | 2000 | 0.5214          | 0.8035   | 0.7299    | 0.8935 | 0.7720   | 0.8064 | 0.7516 |
| 0.4665        | 1.0517 | 2500 | 0.4835          | 0.8199   | 0.8304    | 0.8097 | 0.8145   | 0.8676 | 0.8310 |
| 0.463         | 1.2621 | 3000 | 0.4728          | 0.8318   | 0.7679    | 0.9073 | 0.8086   | 0.8709 | 0.8363 |
| 0.441         | 1.4724 | 3500 | 0.4638          | 0.8316   | 0.8067    | 0.8581 | 0.8187   | 0.8770 | 0.8401 |
| 0.4178        | 1.6828 | 4000 | 0.4333          | 0.8358   | 0.8040    | 0.8702 | 0.8216   | 0.8940 | 0.8833 |
| 0.4165        | 1.8931 | 4500 | 0.4512          | 0.8387   | 0.8095    | 0.8702 | 0.8254   | 0.8851 | 0.8599 |
| 0.4082        | 2.1035 | 5000 | 0.4773          | 0.8361   | 0.8288    | 0.8435 | 0.8275   | 0.8801 | 0.8592 |
| 0.4006        | 2.3138 | 5500 | 0.4735          | 0.8453   | 0.8066    | 0.8879 | 0.8305   | 0.8766 | 0.8257 |
| 0.4053        | 2.5242 | 6000 | 0.4654          | 0.8500   | 0.8033    | 0.9024 | 0.8338   | 0.8930 | 0.8661 |
| 0.4101        | 2.7345 | 6500 | 0.4794          | 0.8493   | 0.8059    | 0.8976 | 0.8338   | 0.8637 | 0.8114 |
| 0.4299        | 2.9449 | 7000 | 0.5050          | 0.8069   | 0.8732    | 0.75   | 0.8128   | 0.9019 | 0.8977 |
| 0.3828        | 3.1552 | 7500 | 0.6362          | 0.7813   | 0.8957    | 0.6927 | 0.7976   | 0.8789 | 0.8808 |
| 0.4132        | 3.3656 | 8000 | 0.4565          | 0.8484   | 0.8130    | 0.8871 | 0.8347   | 0.9009 | 0.8765 |
| 0.383         | 3.5759 | 8500 | 0.4693          | 0.8489   | 0.8151    | 0.8855 | 0.8355   | 0.8880 | 0.8543 |


### Framework versions

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