metadata
license: mit
base_model: xlm-roberta-large
tags:
- generated_from_trainer
datasets:
- wikiann
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: xlm-roberta-large-ner-silvanus
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: wikiann
type: wikiann
config: id
split: validation
args: id
metrics:
- name: Precision
type: precision
value: 0.969802244788883
- name: Recall
type: recall
value: 0.9789587267332075
- name: F1
type: f1
value: 0.9743589743589745
- name: Accuracy
type: accuracy
value: 0.9894519740718916
xlm-roberta-large-ner-silvanus
This model is a fine-tuned version of xlm-roberta-large on the wikiann dataset. It achieves the following results on the evaluation set:
- Loss: 0.0686
- Precision: 0.9698
- Recall: 0.9790
- F1: 0.9744
- Accuracy: 0.9895
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 427 | 0.0717 | 0.9367 | 0.9701 | 0.9531 | 0.9862 |
| 0.0221 | 2.0 | 855 | 0.0715 | 0.9560 | 0.9733 | 0.9646 | 0.9880 |
| 0.0113 | 3.0 | 1281 | 0.0686 | 0.9698 | 0.9790 | 0.9744 | 0.9895 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1