README.md

---
language:
- es
license: cc-by-4.0
tags:
- generated_from_trainer
datasets:
- jorgeortizfuentes/toxicity_spanish_hate_speech_v2
metrics:
- f1
base_model: dccuchile/patana-chilean-spanish-bert
model-index:
- name: hate_speech-dv2-patana-chilean-spanish-bert-8k0iqdv2
  results:
  - task:
      type: text-classification
      name: Text Classification
    dataset:
      name: jorgeortizfuentes/toxicity_spanish_hate_speech_v2
      type: jorgeortizfuentes/toxicity_spanish_hate_speech_v2
      split: validation
    metrics:
    - type: f1
      value: 0.8160919540229885
      name: F1
---

<!-- 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. -->

# hate_speech-dv2-patana-chilean-spanish-bert-8k0iqdv2

This model is a fine-tuned version of [dccuchile/patana-chilean-spanish-bert](https://huggingface.co/dccuchile/patana-chilean-spanish-bert) on the jorgeortizfuentes/toxicity_spanish_hate_speech_v2 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1628
- F1: 0.8161

## 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: 4e-05
- train_batch_size: 128
- eval_batch_size: 128
- seed: 13
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | F1     |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.0528        | 5.0   | 430  | 0.1698          | 0.7376 |
| 0.003         | 10.0  | 860  | 0.1628          | 0.8161 |


### Framework versions

- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3