---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- wl
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: spanish-clinical-ner
  results:
  - task:
      name: Token Classification
      type: token-classification
    dataset:
      name: wl
      type: wl
      config: WL
      split: train
      args: WL
    metrics:
    - name: Precision
      type: precision
      value: 0.6868542362104594
    - name: Recall
      type: recall
      value: 0.7348639455782313
    - name: F1
      type: f1
      value: 0.7100484758853013
    - name: Accuracy
      type: accuracy
      value: 0.8262735659847573
---

<!-- 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. -->

# spanish-clinical-ner

This model is a fine-tuned version of [plncmm/roberta-clinical-wl-es](https://huggingface.co/plncmm/roberta-clinical-wl-es) on the wl dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6181
- Precision: 0.6869
- Recall: 0.7349
- F1: 0.7100
- Accuracy: 0.8263

## 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
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 1.0283        | 1.0   | 500  | 0.6862          | 0.6690    | 0.6959 | 0.6822 | 0.8091   |
| 0.599         | 2.0   | 1000 | 0.6198          | 0.6856    | 0.7276 | 0.7059 | 0.8252   |
| 0.4973        | 3.0   | 1500 | 0.6181          | 0.6869    | 0.7349 | 0.7100 | 0.8263   |


### Framework versions

- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.6.1
- Tokenizers 0.13.2