---
library_name: transformers
license: apache-2.0
base_model: markusbayer/CySecBERT
tags:
- generated_from_trainer
metrics:
- precision
- recall
model-index:
- name: cysecbert-ttp
  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. -->

# cysecbert-ttp

This model is a fine-tuned version of [markusbayer/CySecBERT](https://huggingface.co/markusbayer/CySecBERT) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0182
- F1 Micro: 0.3613
- F1 Macro: 0.0811
- Precision: 0.7753
- Recall: 0.2355

## 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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | Precision | Recall |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------:|:------:|
| 0.0359        | 1.0   | 1226 | 0.0316          | 0.0      | 0.0      | 0.0       | 0.0    |
| 0.0278        | 2.0   | 2452 | 0.0278          | 0.0202   | 0.0036   | 0.8571    | 0.0102 |
| 0.0242        | 3.0   | 3678 | 0.0230          | 0.2709   | 0.0438   | 0.7462    | 0.1655 |
| 0.0233        | 4.0   | 4904 | 0.0193          | 0.2881   | 0.0567   | 0.8361    | 0.1741 |
| 0.0186        | 5.0   | 6130 | 0.0182          | 0.3613   | 0.0811   | 0.7753    | 0.2355 |


### Framework versions

- Transformers 4.57.5
- Pytorch 2.2.0
- Datasets 4.5.0
- Tokenizers 0.22.2