metadata
library_name: transformers
license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
- generated_from_trainer
datasets:
- conll2002
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: xlm-roberta-large-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: 0.86443345323741
- name: Recall
type: recall
value: 0.8835018382352942
- name: F1
type: f1
value: 0.8738636363636364
- name: Accuracy
type: accuracy
value: 0.9787686065955755
xlm-roberta-large-finetuned-ner
This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the conll2002 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0973
- Precision: 0.8644
- Recall: 0.8835
- F1: 0.8739
- Accuracy: 0.9788
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: 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1382 | 1.0 | 521 | 0.0906 | 0.8502 | 0.8830 | 0.8663 | 0.9782 |
| 0.048 | 2.0 | 1042 | 0.0861 | 0.8472 | 0.8729 | 0.8599 | 0.9780 |
| 0.0294 | 3.0 | 1563 | 0.0973 | 0.8644 | 0.8835 | 0.8739 | 0.9788 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1
- Datasets 3.1.0
- Tokenizers 0.20.3