---
library_name: transformers
license: mit
base_model: urduhack/roberta-urdu-small
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: roberta-urdu-small-clf
  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. -->

# roberta-urdu-small-clf

This model is a fine-tuned version of [urduhack/roberta-urdu-small](https://huggingface.co/urduhack/roberta-urdu-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7478
- Accuracy: 0.7945
- Macro F1: 0.7322

## 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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
| No log        | 1.0   | 247  | 1.0007          | 0.6849   | 0.5277   |
| No log        | 2.0   | 494  | 0.6376          | 0.7648   | 0.6772   |
| 1.3343        | 3.0   | 741  | 0.5805          | 0.7968   | 0.7311   |
| 1.3343        | 4.0   | 988  | 0.6192          | 0.8037   | 0.7334   |
| 0.3891        | 5.0   | 1235 | 0.6002          | 0.7968   | 0.7313   |
| 0.3891        | 6.0   | 1482 | 0.7478          | 0.7945   | 0.7322   |


### Framework versions

- Transformers 4.52.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1