metadata
license: apache-2.0
base_model: VerificadoProfesional/SaBERT-Spanish-Sentiment-Analysis
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: my-model-Sabert-Sentimento
results: []
my-model-Sabert-Sentimento
This model is a fine-tuned version of VerificadoProfesional/SaBERT-Spanish-Sentiment-Analysis on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3425
- Accuracy: 0.9355
- F1: 0.9276
- Precision: 0.9253
- 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: 0.0002
- train_batch_size: 30
- eval_batch_size: 10
- 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 |
---|---|---|---|---|---|---|---|
0.4095 | 1.0 | 25 | 0.2597 | 0.9355 | 0.9276 | 0.9253 | 0.9355 |
0.1831 | 2.0 | 50 | 0.3267 | 0.9226 | 0.9024 | 0.9223 | 0.9226 |
0.138 | 3.0 | 75 | 0.3843 | 0.9290 | 0.9125 | 0.9278 | 0.9290 |
0.0776 | 4.0 | 100 | 0.3418 | 0.9290 | 0.9240 | 0.9199 | 0.9290 |
0.0561 | 5.0 | 125 | 0.3425 | 0.9355 | 0.9276 | 0.9253 | 0.9355 |
Framework versions
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1