---
library_name: transformers
license: cc-by-4.0
base_model: bertin-project/bertin-roberta-base-spanish
tags:
- generated_from_trainer
metrics:
- recall
- precision
model-index:
- name: clasificador-ser-estar-window-3-bert-base
  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. -->

# clasificador-ser-estar-window-3-bert-base

This model is a fine-tuned version of [bertin-project/bertin-roberta-base-spanish](https://huggingface.co/bertin-project/bertin-roberta-base-spanish) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4157
- F1 Score: 0.8543
- Recall: 0.9030
- Precision: 0.8106
- Roc Auc: 0.8863

## 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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 20

### Training results

| Training Loss | Epoch | Step | Validation Loss | F1 Score | Recall | Precision | Roc Auc |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:-------:|
| No log        | 1.0   | 25   | 0.6771          | 0.7465   | 1.0    | 0.5955    | 0.6521  |
| No log        | 2.0   | 50   | 0.5844          | 0.8035   | 0.9662 | 0.6877    | 0.8265  |
| No log        | 3.0   | 75   | 0.4922          | 0.7736   | 0.7426 | 0.8073    | 0.8561  |
| No log        | 4.0   | 100  | 0.4157          | 0.8543   | 0.9030 | 0.8106    | 0.8863  |
| No log        | 5.0   | 125  | 0.4810          | 0.7824   | 0.7511 | 0.8165    | 0.8607  |
| No log        | 6.0   | 150  | 0.5954          | 0.8110   | 0.8059 | 0.8162    | 0.8225  |
| No log        | 7.0   | 175  | 0.4667          | 0.8384   | 0.8650 | 0.8135    | 0.8697  |
| No log        | 8.0   | 200  | 0.4872          | 0.8370   | 0.8776 | 0.8       | 0.8737  |
| No log        | 9.0   | 225  | 0.6294          | 0.8488   | 0.9241 | 0.7849    | 0.8860  |
| No log        | 10.0  | 250  | 0.5427          | 0.8167   | 0.8270 | 0.8066    | 0.8718  |
| No log        | 11.0  | 275  | 0.6137          | 0.8511   | 0.9283 | 0.7857    | 0.8900  |
| No log        | 12.0  | 300  | 0.6227          | 0.8444   | 0.8819 | 0.8101    | 0.8876  |
| No log        | 13.0  | 325  | 0.7103          | 0.8151   | 0.8186 | 0.8117    | 0.8313  |
| No log        | 14.0  | 350  | 0.5943          | 0.8433   | 0.9198 | 0.7786    | 0.8752  |
| No log        | 15.0  | 375  | 0.6720          | 0.8413   | 0.8945 | 0.7940    | 0.8826  |
| No log        | 16.0  | 400  | 0.7007          | 0.8466   | 0.9198 | 0.7842    | 0.8782  |
| No log        | 17.0  | 425  | 0.7580          | 0.8454   | 0.9114 | 0.7883    | 0.8816  |
| No log        | 18.0  | 450  | 0.7789          | 0.8454   | 0.9114 | 0.7883    | 0.8803  |
| No log        | 19.0  | 475  | 0.7755          | 0.8482   | 0.9198 | 0.7870    | 0.8808  |
| 0.2871        | 20.0  | 500  | 0.7752          | 0.8488   | 0.9241 | 0.7849    | 0.8797  |


### Framework versions

- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0