xlm-robert-base-finetuned-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: 0.1502
- Precision: 0.8034
- Recall: 0.8422
- F1: 0.8224
- Accuracy: 0.9533
Model description
xlm-robert-base-finetuned-ner with striped conl2003 dataset
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: 8
- eval_batch_size: 8
- 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 | 125 | 0.2659 | 0.6903 | 0.7430 | 0.7157 | 0.9328 |
| No log | 2.0 | 250 | 0.1728 | 0.7926 | 0.8168 | 0.8045 | 0.9503 |
| No log | 3.0 | 375 | 0.1502 | 0.8034 | 0.8422 | 0.8224 | 0.9533 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3