---
license: mit
language:
- uz
metrics:
- precision
- recall
- f1
base_model:
- FacebookAI/xlm-roberta-base
library_name: transformers
---

# xlm-roberta-base-lowercase

This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.16673
- Precision: 0.5710
- Recall: 0.6137
- F1: 0.5916

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- 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_steps: 500
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
| 0.1949        | 1.0   | 2206 | 0.1788          | 0.5315    | 0.5391 | 0.5353 |
| 0.1669        | 2.0   | 4412 | 0.1670          | 0.5353    | 0.5995 | 0.5656 |
| 0.1361        | 3.0   | 6618 | 0.1667          | 0.5710    | 0.6137 | 0.5916 |

### Framework versions

- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0