metadata
license: mit
base_model: xlm-roberta-large
tags:
- generated_from_trainer
model-index:
- name: fine_tuned_XLMROBERTA_cs_wikann
results: []
datasets:
- wikiann
language:
- cs
pipeline_tag: token-classification
fine_tuned_XLMROBERTA_cs_wikann
This model is a fine-tuned version of xlm-roberta-large on an wikiann dataset. It achieves the following results on the evaluation set:
- Loss: 0.1216
- Overall Precision: 0.8919
- Overall Recall: 0.9190
- Overall F1: 0.9053
- Overall Accuracy: 0.9672
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|---|---|---|---|---|---|---|---|
| 0.3409 | 0.4 | 500 | 0.1931 | 0.7764 | 0.8465 | 0.8100 | 0.9495 |
| 0.1816 | 0.8 | 1000 | 0.1427 | 0.8405 | 0.8793 | 0.8595 | 0.9576 |
| 0.1401 | 1.2 | 1500 | 0.1273 | 0.8758 | 0.9068 | 0.8910 | 0.9651 |
| 0.1088 | 1.6 | 2000 | 0.1392 | 0.8868 | 0.9139 | 0.9001 | 0.9662 |
| 0.1027 | 2.0 | 2500 | 0.1096 | 0.8929 | 0.9233 | 0.9078 | 0.9699 |
| 0.0667 | 2.4 | 3000 | 0.1267 | 0.9030 | 0.9268 | 0.9148 | 0.9699 |
| 0.0601 | 2.8 | 3500 | 0.1203 | 0.9078 | 0.9326 | 0.9200 | 0.9712 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0