metadata
license: apache-2.0
base_model: somosnlp-hackathon-2022/twitter_sexismo-finetuned-robertuito-exist2021
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: NewSpanishFinetunedtrainepoch10
results: []
NewSpanishFinetunedtrainepoch10
This model is a fine-tuned version of somosnlp-hackathon-2022/twitter_sexismo-finetuned-robertuito-exist2021 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9422
- Accuracy: 0.7818
- F1: 0.7723
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: 64
- 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 | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 390 | 2.2975 | 0.75 | 0.7280 |
| 0.0373 | 2.0 | 780 | 1.6730 | 0.7645 | 0.7570 |
| 0.0227 | 3.0 | 1170 | 1.6890 | 0.7688 | 0.7536 |
| 0.0303 | 4.0 | 1560 | 1.6623 | 0.7659 | 0.7573 |
| 0.0303 | 5.0 | 1950 | 1.4957 | 0.7717 | 0.7588 |
| 0.0133 | 6.0 | 2340 | 1.8339 | 0.7731 | 0.7627 |
| 0.0086 | 7.0 | 2730 | 1.9297 | 0.7717 | 0.7651 |
| 0.0031 | 8.0 | 3120 | 1.8540 | 0.7775 | 0.7677 |
| 0.0021 | 9.0 | 3510 | 1.9277 | 0.7803 | 0.7704 |
| 0.0021 | 10.0 | 3900 | 1.9422 | 0.7818 | 0.7723 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1