metadata
base_model: cardiffnlp/twitter-xlm-roberta-base-sentiment
tags:
- generated_from_trainer
model-index:
- name: Analisis-sentimientos-XLM-Roberta-TASS-C
results: []
Analisis-sentimientos-XLM-Roberta-TASS-C
This model is a fine-tuned version of cardiffnlp/twitter-xlm-roberta-base-sentiment on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0906
- Rmse: 1.2160
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Rmse |
|---|---|---|---|---|
| 1.0289 | 1.0 | 961 | 0.9978 | 0.8375 |
| 1.0696 | 2.0 | 1922 | 1.0969 | 0.8262 |
| 1.1009 | 3.0 | 2883 | 1.0907 | 1.2160 |
| 1.101 | 4.0 | 3844 | 1.0909 | 1.2160 |
| 1.1021 | 5.0 | 4805 | 1.0911 | 1.2160 |
| 1.096 | 6.0 | 5766 | 1.0933 | 1.2160 |
| 1.0964 | 7.0 | 6727 | 1.0909 | 1.2160 |
| 1.0953 | 8.0 | 7688 | 1.0912 | 1.2160 |
| 1.0929 | 9.0 | 8649 | 1.0907 | 1.2160 |
| 1.0921 | 10.0 | 9610 | 1.0906 | 1.2160 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.18.0
- Tokenizers 0.13.3