metadata
license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: roberta-large-finetuned-ner-vlsp2021-3090-13June-1
results: []
roberta-large-finetuned-ner-vlsp2021-3090-13June-1
This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1047
- Precision: 0.8600
- Recall: 0.8655
- F1: 0.8628
- Accuracy: 0.9807
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: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0934 | 1.0 | 3263 | 0.0816 | 0.8165 | 0.8385 | 0.8274 | 0.9774 |
| 0.0605 | 2.0 | 6526 | 0.0806 | 0.8521 | 0.8403 | 0.8461 | 0.9787 |
| 0.0389 | 3.0 | 9789 | 0.0866 | 0.8631 | 0.8512 | 0.8571 | 0.9797 |
| 0.0243 | 4.0 | 13052 | 0.0969 | 0.8700 | 0.8596 | 0.8648 | 0.9803 |
| 0.0166 | 5.0 | 16315 | 0.1047 | 0.8600 | 0.8655 | 0.8628 | 0.9807 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1