license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
datasets:
- wikiann
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: xlm-roberta-base-ka-ner
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: wikiann
type: wikiann
config: ka
split: validation
args: ka
metrics:
- name: Precision
type: precision
value: 0.8505682876839947
- name: Recall
type: recall
value: 0.8702816057519472
- name: F1
type: f1
value: 0.8603120330609663
- name: Accuracy
type: accuracy
value: 0.9424682155180856
language:
- ka
xlm-roberta-base-ka-ner
This model is a fine-tuned version of xlm-roberta-base on the wikiann dataset. It achieves the following results on the evaluation set:
- Loss: 0.2031
- Precision: 0.8506
- Recall: 0.8703
- F1: 0.8603
- Accuracy: 0.9425
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 |
|---|---|---|---|---|---|---|---|
| 0.5349 | 1.0 | 625 | 0.2377 | 0.8302 | 0.8218 | 0.8260 | 0.9287 |
| 0.2353 | 2.0 | 1250 | 0.2037 | 0.8556 | 0.8536 | 0.8546 | 0.9394 |
| 0.1782 | 3.0 | 1875 | 0.2031 | 0.8506 | 0.8703 | 0.8603 | 0.9425 |
Metrics per category
{'LOC': {'precision': 0.8558191459670667, 'recall': 0.9074874223142941, 'f1': 0.8808962941683425, 'number': 16895}, 'ORG': {'precision': 0.7917612346799818, 'recall': 0.7510226049515608, 'f1': 0.7708540492763231, 'number': 9290}, 'PER': {'precision': 0.8896882494004796, 'recall': 0.9157884743188076, 'f1': 0.9025497076023392, 'number': 10533}, 'overall_precision': 0.8505682876839947, 'overall_recall': 0.8702816057519472, 'overall_f1': 0.8603120330609663, 'overall_accuracy': 0.9424682155180856}
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0