---
license: apache-2.0
base_model: projecte-aina/roberta-base-ca-v2-cased-te
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: 2504separado3
  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. -->

# 2504separado3

This model is a fine-tuned version of [projecte-aina/roberta-base-ca-v2-cased-te](https://huggingface.co/projecte-aina/roberta-base-ca-v2-cased-te) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6752
- Accuracy: 0.8445
- Precision: 0.8451
- Recall: 0.8445
- F1: 0.8445
- Ratio: 0.5210

## 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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 4
- label_smoothing_factor: 0.1

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     | Ratio  |
|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|
| 0.404         | 0.9870 | 38   | 0.7068          | 0.8151   | 0.8174    | 0.8151 | 0.8148 | 0.5420 |
| 0.3648        | 2.0    | 77   | 0.6934          | 0.8277   | 0.8317    | 0.8277 | 0.8272 | 0.5546 |
| 0.3989        | 2.9870 | 115  | 0.6752          | 0.8445   | 0.8451    | 0.8445 | 0.8445 | 0.5210 |
| 0.4125        | 3.9481 | 152  | 0.6799          | 0.8361   | 0.8367    | 0.8361 | 0.8361 | 0.5210 |


### Framework versions

- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1