metadata
license: cc-by-4.0
tags:
- generated_from_trainer
metrics:
- f1
- recall
- accuracy
- precision
model-index:
- name: bertin-roberta-fine-tuned-text-classification-SL-data-augmentation-test-3
results: []
bertin-roberta-fine-tuned-text-classification-SL-data-augmentation-test-3
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: 3.5287
- F1: 0.4018
- Recall: 0.3146
- Accuracy: 0.3146
- Precision: 0.6085
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 |
|---|---|---|---|---|---|---|---|
| 2.1331 | 1.0 | 1546 | 3.1241 | 0.3069 | 0.2550 | 0.2550 | 0.4860 |
| 1.5436 | 2.0 | 3092 | 2.8434 | 0.3705 | 0.3091 | 0.3091 | 0.5677 |
| 0.9374 | 3.0 | 4638 | 2.8335 | 0.3988 | 0.3280 | 0.3280 | 0.5673 |
| 0.5072 | 4.0 | 6184 | 2.9788 | 0.4117 | 0.3359 | 0.3359 | 0.5901 |
| 0.27 | 5.0 | 7730 | 3.5287 | 0.4018 | 0.3146 | 0.3146 | 0.6085 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3