metadata
license: mit
base_model: xlm-roberta-large
tags:
- generated_from_trainer
datasets:
- conll2003
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: xlm-roberta-large-finetuned-conll2003
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: conll2003
type: conll2003
config: conll2003
split: validation
args: conll2003
metrics:
- name: Precision
type: precision
value: 0.9620781824256599
- name: Recall
type: recall
value: 0.9692022887916526
- name: F1
type: f1
value: 0.9656270959087861
- name: Accuracy
type: accuracy
value: 0.9936723647833028
xlm-roberta-large-finetuned-conll2003
This model is a fine-tuned version of xlm-roberta-large on the conll2003 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0412
- Precision: 0.9621
- Recall: 0.9692
- F1: 0.9656
- Accuracy: 0.9937
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: 6
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
0.1591 | 1.0 | 896 | 0.0440 | 0.9388 | 0.9451 | 0.9420 | 0.9896 |
0.0335 | 2.0 | 1792 | 0.0361 | 0.9512 | 0.9586 | 0.9549 | 0.9924 |
0.0195 | 3.0 | 2688 | 0.0378 | 0.9570 | 0.9636 | 0.9603 | 0.9931 |
0.0104 | 4.0 | 3584 | 0.0396 | 0.9587 | 0.9613 | 0.9600 | 0.9928 |
0.0064 | 5.0 | 4480 | 0.0400 | 0.9617 | 0.9675 | 0.9646 | 0.9937 |
0.0032 | 6.0 | 5376 | 0.0412 | 0.9621 | 0.9692 | 0.9656 | 0.9937 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0