|
--- |
|
base_model: pysentimiento/robertuito-sentiment-analysis |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
model-index: |
|
- name: roBERTuito-Meta4Types-ft-ES |
|
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. --> |
|
|
|
# roBERTuito-Meta4Types-ft-ES |
|
|
|
This model is a fine-tuned version of [pysentimiento/robertuito-sentiment-analysis](https://huggingface.co/pysentimiento/robertuito-sentiment-analysis) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8547 |
|
- Roc Auc: 0.6496 |
|
- Hamming Loss: 0.1830 |
|
- F1 Score: 0.5653 |
|
- Accuracy: 0.5931 |
|
- Precision: 0.6214 |
|
- Recall: 0.5298 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Roc Auc | Hamming Loss | F1 Score | Accuracy | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------------:|:--------:|:--------:|:---------:|:------:| |
|
| No log | 1.0 | 204 | 0.5044 | 0.5 | 0.2026 | 0.2930 | 0.6176 | 0.9281 | 0.3333 | |
|
| No log | 2.0 | 408 | 0.4634 | 0.5717 | 0.1961 | 0.4829 | 0.6225 | 0.5819 | 0.4651 | |
|
| 0.4697 | 3.0 | 612 | 0.4784 | 0.6173 | 0.1748 | 0.4993 | 0.6275 | 0.8438 | 0.4596 | |
|
| 0.4697 | 4.0 | 816 | 0.6585 | 0.6129 | 0.2124 | 0.5351 | 0.5539 | 0.5456 | 0.5279 | |
|
| 0.1464 | 5.0 | 1020 | 0.8070 | 0.5891 | 0.2010 | 0.4963 | 0.6078 | 0.5732 | 0.4703 | |
|
| 0.1464 | 6.0 | 1224 | 0.7848 | 0.6094 | 0.1912 | 0.5294 | 0.5735 | 0.5916 | 0.4989 | |
|
| 0.1464 | 7.0 | 1428 | 0.8547 | 0.6496 | 0.1830 | 0.5653 | 0.5931 | 0.6214 | 0.5298 | |
|
| 0.0278 | 8.0 | 1632 | 0.9068 | 0.6152 | 0.1846 | 0.5396 | 0.5784 | 0.6114 | 0.5064 | |
|
| 0.0278 | 9.0 | 1836 | 0.9251 | 0.6110 | 0.1961 | 0.5258 | 0.5588 | 0.5674 | 0.5023 | |
|
| 0.0029 | 10.0 | 2040 | 0.9343 | 0.6146 | 0.1944 | 0.5276 | 0.5686 | 0.5751 | 0.5002 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.43.3 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
