---
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_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-bigbird-base-t2t_ft_BioS74_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: 0.3903
- F1 Score: 0.8369
- Precision: 0.8479
- Recall: 0.8262
- Accuracy: 0.8314
- Auc: 0.9159
- Prc: 0.9150

## 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    |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
| 0.5065        | 0.1314 | 500  | 0.4874          | 0.8094   | 0.8042    | 0.8147 | 0.7991   | 0.8745 | 0.8648 |
| 0.4714        | 0.2629 | 1000 | 0.5169          | 0.7982   | 0.8196    | 0.7780 | 0.7941   | 0.8816 | 0.8741 |
| 0.4608        | 0.3943 | 1500 | 0.4256          | 0.8224   | 0.8137    | 0.8312 | 0.8120   | 0.8906 | 0.8850 |
| 0.4365        | 0.5258 | 2000 | 0.5043          | 0.8323   | 0.7431    | 0.9458 | 0.8004   | 0.8970 | 0.8898 |
| 0.4181        | 0.6572 | 2500 | 0.4206          | 0.8438   | 0.7824    | 0.9156 | 0.8225   | 0.9004 | 0.8946 |
| 0.4426        | 0.7886 | 3000 | 0.3973          | 0.8417   | 0.8253    | 0.8589 | 0.8309   | 0.9043 | 0.9005 |
| 0.4192        | 0.9201 | 3500 | 0.4847          | 0.8416   | 0.8209    | 0.8634 | 0.8299   | 0.9065 | 0.9000 |
| 0.4267        | 1.0515 | 4000 | 0.4880          | 0.8264   | 0.8417    | 0.8117 | 0.8215   | 0.9053 | 0.8978 |
| 0.3992        | 1.1830 | 4500 | 0.3852          | 0.8443   | 0.8152    | 0.8754 | 0.8309   | 0.9103 | 0.9095 |
| 0.3973        | 1.3144 | 5000 | 0.4035          | 0.8341   | 0.8335    | 0.8348 | 0.8262   | 0.9100 | 0.9086 |
| 0.3861        | 1.4458 | 5500 | 0.4904          | 0.8187   | 0.8696    | 0.7735 | 0.8207   | 0.9114 | 0.9103 |
| 0.3703        | 1.5773 | 6000 | 0.4456          | 0.8306   | 0.8466    | 0.8152 | 0.8259   | 0.9130 | 0.9100 |
| 0.3964        | 1.7087 | 6500 | 0.3778          | 0.8371   | 0.8368    | 0.8373 | 0.8293   | 0.9143 | 0.9142 |
| 0.3744        | 1.8402 | 7000 | 0.3903          | 0.8369   | 0.8479    | 0.8262 | 0.8314   | 0.9159 | 0.9150 |


### Framework versions

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