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: 0.4357
- Rmse: 0.4405
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 |
|---|---|---|---|---|
| 0.2283 | 1.0 | 642 | 0.2403 | 0.5230 |
| 0.1594 | 2.0 | 1284 | 0.2210 | 0.4827 |
| 0.1136 | 3.0 | 1926 | 0.2536 | 0.4441 |
| 0.0833 | 4.0 | 2568 | 0.2490 | 0.4370 |
| 0.0536 | 5.0 | 3210 | 0.3226 | 0.4370 |
| 0.0439 | 6.0 | 3852 | 0.3494 | 0.4388 |
| 0.0336 | 7.0 | 4494 | 0.4017 | 0.4352 |
| 0.033 | 8.0 | 5136 | 0.4274 | 0.4388 |
| 0.0307 | 9.0 | 5778 | 0.4120 | 0.4334 |
| 0.0274 | 10.0 | 6420 | 0.4357 | 0.4405 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.0.1+cu117
- Datasets 2.18.0
- Tokenizers 0.19.1