---
library_name: transformers
license: apache-2.0
base_model: nickprock/setfit-italian-hate-speech
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: MultiPRIDE-baseline-it
  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. -->

# MultiPRIDE-baseline-it

This model is a fine-tuned version of [nickprock/setfit-italian-hate-speech](https://huggingface.co/nickprock/setfit-italian-hate-speech) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6297
- Accuracy: 0.9325
- F1: 0.8831
- Precision: 0.9131
- Recall: 0.8596

## 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: 150
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 0.4607        | 1.0   | 95   | 0.3423          | 0.9264   | 0.8742 | 0.8965    | 0.8558 |
| 0.2351        | 2.0   | 190  | 0.4198          | 0.9325   | 0.8831 | 0.9131    | 0.8596 |
| 0.201         | 3.0   | 285  | 0.1992          | 0.9632   | 0.9430 | 0.9247    | 0.9649 |
| 0.1004        | 4.0   | 380  | 0.4917          | 0.9202   | 0.8535 | 0.9155    | 0.8150 |
| 0.1           | 5.0   | 475  | 0.3548          | 0.9387   | 0.8979 | 0.9086    | 0.8881 |
| 0.0438        | 6.0   | 570  | 0.6297          | 0.9325   | 0.8831 | 0.9131    | 0.8596 |


### Framework versions

- Transformers 4.57.3
- Pytorch 2.9.1+cu128
- Datasets 4.4.1
- Tokenizers 0.22.1