metadata
library_name: transformers
license: mit
base_model: xlm-roberta-large
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: xlm-roberta-large-finetuned-ner-biomedical-spanish
results: []
xlm-roberta-large-finetuned-ner-biomedical-spanish
This model is a fine-tuned version of xlm-roberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0806
- Precision: 0.9458
- Recall: 0.9735
- F1: 0.9595
- Accuracy: 0.9811
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: 20
- eval_batch_size: 20
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 490 | 0.0902 | 0.9397 | 0.9559 | 0.9477 | 0.9756 |
| 0.2921 | 2.0 | 980 | 0.0931 | 0.9369 | 0.9725 | 0.9544 | 0.9780 |
| 0.09 | 3.0 | 1470 | 0.0806 | 0.9458 | 0.9735 | 0.9595 | 0.9811 |
| 0.0646 | 4.0 | 1960 | 0.0844 | 0.9433 | 0.9702 | 0.9566 | 0.9791 |
| 0.0492 | 5.0 | 2450 | 0.0860 | 0.9440 | 0.9698 | 0.9567 | 0.9797 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3