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

# gena-lm-bigbird-base-t2t_ft_BioS73_1kbpHG19_DHSs_H3K27AC

This model is a fine-tuned version of [AIRI-Institute/gena-lm-bigbird-base-t2t](https://huggingface.co/AIRI-Institute/gena-lm-bigbird-base-t2t) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6204
- F1 Score: 0.8827
- Precision: 0.8652
- Recall: 0.9008
- Accuracy: 0.8722
- Auc: 0.9384
- Prc: 0.9368

## 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    |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
| 0.4735        | 0.1864 | 500  | 0.4718          | 0.8258   | 0.7264    | 0.9567 | 0.7846   | 0.8950 | 0.8902 |
| 0.4071        | 0.3727 | 1000 | 0.4255          | 0.8534   | 0.7923    | 0.9246 | 0.8304   | 0.9117 | 0.9095 |
| 0.391         | 0.5591 | 1500 | 0.4176          | 0.8508   | 0.8496    | 0.8520 | 0.8405   | 0.9184 | 0.9132 |
| 0.3833        | 0.7454 | 2000 | 0.3674          | 0.8655   | 0.8235    | 0.9120 | 0.8487   | 0.9209 | 0.9082 |
| 0.3812        | 0.9318 | 2500 | 0.4179          | 0.8652   | 0.7974    | 0.9455 | 0.8427   | 0.9255 | 0.9217 |
| 0.3673        | 1.1182 | 3000 | 0.3696          | 0.8714   | 0.8180    | 0.9323 | 0.8531   | 0.9295 | 0.9266 |
| 0.3469        | 1.3045 | 3500 | 0.3985          | 0.8696   | 0.8121    | 0.9358 | 0.8502   | 0.9324 | 0.9307 |
| 0.3452        | 1.4909 | 4000 | 0.3347          | 0.8724   | 0.8685    | 0.8764 | 0.8632   | 0.9327 | 0.9316 |
| 0.3241        | 1.6772 | 4500 | 0.4804          | 0.8753   | 0.8316    | 0.9239 | 0.8595   | 0.9350 | 0.9341 |
| 0.3529        | 1.8636 | 5000 | 0.4180          | 0.8789   | 0.8330    | 0.9302 | 0.8632   | 0.9366 | 0.9364 |
| 0.3102        | 2.0499 | 5500 | 0.5486          | 0.8851   | 0.8460    | 0.9281 | 0.8714   | 0.9378 | 0.9371 |
| 0.3217        | 2.2363 | 6000 | 0.5019          | 0.8856   | 0.8498    | 0.9246 | 0.8725   | 0.9390 | 0.9369 |
| 0.272         | 2.4227 | 6500 | 0.4057          | 0.8844   | 0.8591    | 0.9113 | 0.8729   | 0.9416 | 0.9410 |
| 0.303         | 2.6090 | 7000 | 0.5302          | 0.8806   | 0.8187    | 0.9525 | 0.8621   | 0.9372 | 0.9321 |
| 0.2944        | 2.7954 | 7500 | 0.4633          | 0.8819   | 0.8676    | 0.8966 | 0.8718   | 0.9405 | 0.9392 |
| 0.269         | 2.9817 | 8000 | 0.5419          | 0.8756   | 0.8042    | 0.9609 | 0.8543   | 0.9432 | 0.9423 |
| 0.2168        | 3.1681 | 8500 | 0.6204          | 0.8827   | 0.8652    | 0.9008 | 0.8722   | 0.9384 | 0.9368 |


### Framework versions

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