metadata
library_name: transformers
license: mit
base_model: xlm-roberta-large
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: x5-ner
results: []
x5-ner
This model is a fine-tuned version of xlm-roberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4700
- Precision: 0.9465
- Recall: 0.9597
- F1: 0.9531
- Accuracy: 0.9525
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1882 | 4.0 | 12264 | 0.2794 | 0.9282 | 0.9477 | 0.9379 | 0.9443 |
| 0.1232 | 5.0 | 15330 | 0.2867 | 0.9391 | 0.9534 | 0.9462 | 0.9504 |
| 0.0967 | 6.0 | 18396 | 0.3523 | 0.9400 | 0.9543 | 0.9471 | 0.9508 |
| 0.0529 | 7.0 | 21462 | 0.3790 | 0.9397 | 0.9585 | 0.9490 | 0.9516 |
| 0.0372 | 8.0 | 24528 | 0.4232 | 0.9454 | 0.9556 | 0.9505 | 0.9518 |
| 0.0238 | 9.0 | 27594 | 0.4425 | 0.9472 | 0.9616 | 0.9544 | 0.9544 |
| 0.0126 | 10.0 | 30660 | 0.4700 | 0.9465 | 0.9597 | 0.9531 | 0.9525 |
Framework versions
- Transformers 4.56.2
- Pytorch 2.7.1+cu118
- Datasets 3.6.0
- Tokenizers 0.22.0