metadata
library_name: transformers
base_model: cardiffnlp/twitter-xlm-roberta-base-hate-spanish
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: MultiPRIDE-DualEncoder-MainStage-es
results: []
MultiPRIDE-DualEncoder-MainStage-es
This model is a fine-tuned version of cardiffnlp/twitter-xlm-roberta-base-hate-spanish on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3704
- Accuracy: 0.8333
- F1: 0.56
- Precision: 0.4667
- Recall: 0.7
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.6609 | 1.0 | 77 | 0.5098 | 0.8636 | 0.5714 | 0.5455 | 0.6 |
| 0.5878 | 2.0 | 154 | 0.4235 | 0.8258 | 0.5818 | 0.4571 | 0.8 |
| 0.5223 | 3.0 | 231 | 0.3988 | 0.8561 | 0.5957 | 0.5185 | 0.7 |
| 0.4915 | 4.0 | 308 | 0.3783 | 0.8409 | 0.5714 | 0.4828 | 0.7 |
| 0.4787 | 5.0 | 385 | 0.3764 | 0.8333 | 0.5926 | 0.4706 | 0.8 |
| 0.4287 | 6.0 | 462 | 0.3704 | 0.8333 | 0.56 | 0.4667 | 0.7 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.1+cu128
- Datasets 4.4.1
- Tokenizers 0.22.1