bkk-buget-ner
This model is a fine-tuned version of xlm-roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0287
- Precision: 0.9796
- Recall: 0.9852
- F1: 0.9824
- Accuracy: 0.9930
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: 0.0001
- 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 118 | 0.0572 | 0.9238 | 0.9738 | 0.9482 | 0.9849 |
| No log | 2.0 | 236 | 0.0281 | 0.9801 | 0.9829 | 0.9815 | 0.9938 |
| No log | 3.0 | 354 | 0.0287 | 0.9796 | 0.9852 | 0.9824 | 0.9930 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2