---
library_name: transformers
language:
- uz
license: mit
base_model: FacebookAI/xlm-roberta-large
tags:
- generated_from_trainer
datasets:
- risqaliyevds/uzbek_ner
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: Uzbek NER model
  results: []
---

<!-- 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. -->

# Uzbek NER model

This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the Uzbek Ner dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1542
- Precision: 0.5799
- Recall: 0.6318
- F1: 0.6047
- Accuracy: 0.9456

## 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: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.5172        | 1.0    | 246  | 0.1644          | 0.5574    | 0.5631 | 0.5602 | 0.9434   |
| 0.1532        | 2.0    | 492  | 0.1551          | 0.5790    | 0.6188 | 0.5982 | 0.9453   |
| 0.143         | 2.9913 | 735  | 0.1542          | 0.5799    | 0.6318 | 0.6047 | 0.9456   |


### Framework versions

- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0