<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
xlm-roberta-base-sv-aug-ner
This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2611
- Precision: 0.6693
- Recall: 0.6664
- F1: 0.6679
- Accuracy: 0.9244
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: 32
- eval_batch_size: 32
- 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 |
---|---|---|---|---|---|---|---|
0.6807 | 1.0 | 804 | 0.3764 | 0.5263 | 0.5183 | 0.5223 | 0.8956 |
0.2691 | 2.0 | 1608 | 0.2995 | 0.6437 | 0.6104 | 0.6266 | 0.9172 |
0.2278 | 3.0 | 2412 | 0.2708 | 0.6494 | 0.6485 | 0.6489 | 0.9226 |
0.1834 | 4.0 | 3216 | 0.2623 | 0.6753 | 0.6549 | 0.6650 | 0.9251 |
0.161 | 5.0 | 4020 | 0.2611 | 0.6693 | 0.6664 | 0.6679 | 0.9244 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2