metadata
license: cc-by-4.0
base_model: bertin-project/bertin-roberta-base-spanish
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: my-model-Bertin-Sentimento
results: []
my-model-Bertin-Sentimento
This model is a fine-tuned version of bertin-project/bertin-roberta-base-spanish on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3572
- Accuracy: 0.9355
- F1: 0.9279
- Precision: 0.9268
- Recall: 0.9355
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
0.3998 | 1.0 | 91 | 0.3293 | 0.8774 | 0.8553 | 0.8570 | 0.8774 |
0.2686 | 2.0 | 182 | 0.2188 | 0.9290 | 0.9200 | 0.9199 | 0.9290 |
0.1113 | 3.0 | 273 | 0.2266 | 0.9290 | 0.9299 | 0.9360 | 0.9290 |
0.0265 | 4.0 | 364 | 0.4089 | 0.9355 | 0.9277 | 0.9293 | 0.9355 |
0.0065 | 5.0 | 455 | 0.3572 | 0.9355 | 0.9279 | 0.9268 | 0.9355 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1