metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- conll2002
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-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: 0.8596766951055231
- name: Recall
type: recall
value: 0.8798253676470589
- name: F1
type: f1
value: 0.8696343402225755
- name: Accuracy
type: accuracy
value: 0.9784573574765641
bert-finetuned-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: 0.0936
- Precision: 0.8597
- Recall: 0.8798
- F1: 0.8696
- Accuracy: 0.9785
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 |
|---|---|---|---|---|---|---|---|
| 0.1004 | 1.0 | 521 | 0.0850 | 0.8579 | 0.8821 | 0.8698 | 0.9782 |
| 0.0336 | 2.0 | 1042 | 0.0849 | 0.8584 | 0.8775 | 0.8679 | 0.9783 |
| 0.0197 | 3.0 | 1563 | 0.0936 | 0.8597 | 0.8798 | 0.8696 | 0.9785 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3