<!-- 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. -->
bertin-roberta-fine-tuned-text-classification-SL-data-augmentation-dss
This model is a fine-tuned version of bertin-project/bertin-roberta-base-spanish on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3050
- F1: 0.4713
- Recall: 0.4797
- Accuracy: 0.4797
- Precision: 0.4820
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Recall | Accuracy | Precision |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 359 | 3.4261 | 0.2636 | 0.3268 | 0.3268 | 0.2780 |
| 3.7358 | 2.0 | 718 | 2.7048 | 0.3631 | 0.4179 | 0.4179 | 0.3773 |
| 2.4772 | 3.0 | 1077 | 2.4578 | 0.4072 | 0.4407 | 0.4407 | 0.4095 |
| 2.4772 | 4.0 | 1436 | 2.3357 | 0.4403 | 0.4545 | 0.4545 | 0.4815 |
| 1.6075 | 5.0 | 1795 | 2.3050 | 0.4713 | 0.4797 | 0.4797 | 0.4820 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
