metadata
language:
- es
tags:
- generated_from_trainer
datasets:
- jorgeortizfuentes/spanish-offensive-language
metrics:
- f1
model-index:
- name: spanish-offensive-language-bert-base-spanish-wwm-cased
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: jorgeortizfuentes/spanish-offensive-language
type: jorgeortizfuentes/spanish-offensive-language
metrics:
- name: F1
type: f1
value: 0.5861096817040292
spanish-offensive-language-bert-base-spanish-wwm-cased
This model is a fine-tuned version of dccuchile/bert-base-spanish-wwm-cased on the jorgeortizfuentes/spanish-offensive-language dataset. It achieves the following results on the evaluation set:
- Loss: 0.7753
- F1: 0.5861
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: 48
- eval_batch_size: 48
- seed: 13
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.6383 | 1.0 | 166 | 0.6105 | 0.4916 |
| 0.5779 | 2.0 | 332 | 0.6027 | 0.5531 |
| 0.4791 | 3.0 | 498 | 0.6503 | 0.5852 |
| 0.3626 | 4.0 | 664 | 0.7753 | 0.5861 |
| 0.2758 | 5.0 | 830 | 0.8416 | 0.5856 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.13.3