metadata
base_model: cardiffnlp/twitter-xlm-roberta-base-sentiment
tags:
- generated_from_trainer
model-index:
- name: Analisis-sentimientos-xml-roberta-2
results: []
Analisis-sentimientos-xml-roberta-2
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: 0.4219
- Rmse: 0.4262
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: 16
- 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 |
|---|---|---|---|---|
| 0.2287 | 1.0 | 642 | 0.2755 | 0.5435 |
| 0.1602 | 2.0 | 1284 | 0.2480 | 0.5064 |
| 0.1118 | 3.0 | 1926 | 0.3581 | 0.4811 |
| 0.0756 | 4.0 | 2568 | 0.2588 | 0.4545 |
| 0.0523 | 5.0 | 3210 | 0.3172 | 0.4370 |
| 0.0427 | 6.0 | 3852 | 0.3430 | 0.4388 |
| 0.0352 | 7.0 | 4494 | 0.3816 | 0.4243 |
| 0.0314 | 8.0 | 5136 | 0.3776 | 0.4206 |
| 0.0292 | 9.0 | 5778 | 0.4168 | 0.4266 |
| 0.0272 | 10.0 | 6420 | 0.4219 | 0.4262 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1