metadata

library_name: transformers
license: apache-2.0
base_model: PlanTL-GOB-ES/roberta-large-bne-capitel-ner
tags:
  - generated_from_trainer
datasets:
  - biobert_json
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: roberta-large-bne-capitel-ner-finetuned-ner
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: biobert_json
          type: biobert_json
          config: Biobert_json
          split: validation
          args: Biobert_json
        metrics:
          - name: Precision
            type: precision
            value: 0.9574114124105806
          - name: Recall
            type: recall
            value: 0.9658741258741259
          - name: F1
            type: f1
            value: 0.961624150607107
          - name: Accuracy
            type: accuracy
            value: 0.9810238869097464

roberta-large-bne-capitel-ner-finetuned-ner

This model is a fine-tuned version of PlanTL-GOB-ES/roberta-large-bne-capitel-ner on the biobert_json dataset. It achieves the following results on the evaluation set:

Loss: 0.0918
Precision: 0.9574
Recall: 0.9659
F1: 0.9616
Accuracy: 0.9810

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: 8
eval_batch_size: 8
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
0.1292	1.0	1224	0.0942	0.9455	0.9528	0.9491	0.9737
0.0813	2.0	2448	0.0960	0.9443	0.9696	0.9568	0.9780
0.0509	3.0	3672	0.0819	0.9559	0.9686	0.9622	0.9814
0.0314	4.0	4896	0.0853	0.9557	0.9694	0.9625	0.9811
0.0196	5.0	6120	0.0918	0.9574	0.9659	0.9616	0.9810

Framework versions

Transformers 4.46.3
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.20.3