metadata

license: apache-2.0
base_model: BSC-LT/roberta-base-bne-capitel-ner
tags:
  - generated_from_trainer
datasets:
  - conll2002
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: roberta-base-bne-capitel-ner
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: conll2002
          type: conll2002
          config: es
          split: validation
          args: es
        metrics:
          - name: Precision
            type: precision
            value: 0.8712310133756518
          - name: Recall
            type: recall
            value: 0.8830422794117647
          - name: F1
            type: f1
            value: 0.8770968846285518
          - name: Accuracy
            type: accuracy
            value: 0.978961189654646

roberta-base-bne-capitel-ner

This model is a fine-tuned version of BSC-LT/roberta-base-bne-capitel-ner on the conll2002 dataset. It achieves the following results on the evaluation set:

Loss: 0.1255
Precision: 0.8712
Recall: 0.8830
F1: 0.8771
Accuracy: 0.9790

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0135	1.0	1041	0.1233	0.8615	0.8803	0.8708	0.9783
0.0111	2.0	2082	0.1099	0.8709	0.8853	0.8781	0.9799
0.0061	3.0	3123	0.1203	0.8569	0.8739	0.8653	0.9781
0.0035	4.0	4164	0.1255	0.8712	0.8830	0.8771	0.9790

Framework versions

Transformers 4.35.0
Pytorch 2.0.1+cu117
Datasets 2.14.4
Tokenizers 0.14.1