metadata
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-DualEncoder-MainStage-it
results: []
MultiPRIDE-DualEncoder-MainStage-it
This model is a fine-tuned version of nickprock/setfit-italian-hate-speech on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1685
- Accuracy: 0.9571
- F1: 0.8814
- Precision: 0.9286
- Recall: 0.8387
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: 1337
- 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 |
|---|---|---|---|---|---|---|---|
| 0.6452 | 1.0 | 95 | 0.5242 | 0.8344 | 0.6197 | 0.55 | 0.7097 |
| 0.5208 | 2.0 | 190 | 0.3521 | 0.8896 | 0.7273 | 0.6857 | 0.7742 |
| 0.4215 | 3.0 | 285 | 0.2637 | 0.9325 | 0.8136 | 0.8571 | 0.7742 |
| 0.3325 | 4.0 | 380 | 0.2138 | 0.9325 | 0.8136 | 0.8571 | 0.7742 |
| 0.2774 | 5.0 | 475 | 0.1805 | 0.9448 | 0.8525 | 0.8667 | 0.8387 |
| 0.2297 | 6.0 | 570 | 0.1846 | 0.9509 | 0.8621 | 0.9259 | 0.8065 |
| 0.3021 | 7.0 | 665 | 0.1664 | 0.9509 | 0.8667 | 0.8966 | 0.8387 |
| 0.2372 | 8.0 | 760 | 0.1697 | 0.9571 | 0.8814 | 0.9286 | 0.8387 |
| 0.2468 | 9.0 | 855 | 0.1688 | 0.9571 | 0.8814 | 0.9286 | 0.8387 |
| 0.2456 | 10.0 | 950 | 0.1685 | 0.9571 | 0.8814 | 0.9286 | 0.8387 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.1+cu128
- Datasets 4.4.1
- Tokenizers 0.22.1