|
--- |
|
license: cc-by-4.0 |
|
tags: |
|
- generated_from_trainer |
|
base_model: bertin-project/bertin-roberta-base-spanish |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: my-model-Bertin-Sentimento |
|
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. --> |
|
|
|
# my-model-Bertin-Sentimento |
|
|
|
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: 0.2665 |
|
- Accuracy: 0.9484 |
|
- F1: 0.8000 |
|
- Precision: 0.9412 |
|
- Recall: 0.6957 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.35 | 1.0 | 91 | 0.2157 | 0.8516 | 0.0 | 0.0 | 0.0 | |
|
| 0.2706 | 2.0 | 182 | 0.4638 | 0.9097 | 0.5625 | 1.0 | 0.3913 | |
|
| 0.136 | 3.0 | 273 | 0.6050 | 0.9032 | 0.5161 | 1.0 | 0.3478 | |
|
| 0.0675 | 4.0 | 364 | 0.3015 | 0.9484 | 0.7895 | 1.0 | 0.6522 | |
|
| 0.0154 | 5.0 | 455 | 0.2665 | 0.9484 | 0.8000 | 0.9412 | 0.6957 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.0 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
