metadata
license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
- generated_from_trainer
datasets:
- cnec
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: CNEC2_0_Supertypes_xlm-roberta-large
results:
- task:
name: Token Classification
type: token-classification
dataset:
name: cnec
type: cnec
config: default
split: test
args: default
metrics:
- name: Precision
type: precision
value: 0.8325581395348837
- name: Recall
type: recall
value: 0.8824979457682827
- name: F1
type: f1
value: 0.8568009573195053
- name: Accuracy
type: accuracy
value: 0.965938712854081
CNEC2_0_Supertypes_xlm-roberta-large
This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the cnec dataset. It achieves the following results on the evaluation set:
- Loss: 0.1992
- Precision: 0.8326
- Recall: 0.8825
- F1: 0.8568
- Accuracy: 0.9659
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- lr_scheduler_warmup_steps: 500
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.5321 | 2.22 | 500 | 0.1641 | 0.7159 | 0.8065 | 0.7585 | 0.9566 |
| 0.1512 | 4.44 | 1000 | 0.1831 | 0.7886 | 0.8611 | 0.8233 | 0.9591 |
| 0.0967 | 6.67 | 1500 | 0.1866 | 0.7628 | 0.8628 | 0.8097 | 0.9596 |
| 0.0637 | 8.89 | 2000 | 0.1586 | 0.8054 | 0.8841 | 0.8429 | 0.9648 |
| 0.0422 | 11.11 | 2500 | 0.1777 | 0.8294 | 0.8648 | 0.8467 | 0.9654 |
| 0.0292 | 13.33 | 3000 | 0.1992 | 0.8326 | 0.8825 | 0.8568 | 0.9659 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0