---
library_name: transformers
license: mit
base_model: TURKCELL/roberta-base-turkish-uncased
tags:
- generated_from_trainer
model-index:
- name: hukukAi
  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. -->

# hukukAi

This model is a fine-tuned version of [TURKCELL/roberta-base-turkish-uncased](https://huggingface.co/TURKCELL/roberta-base-turkish-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 5.7790

## 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: 5e-05
- train_batch_size: 4
- eval_batch_size: 4
- 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 5.1882        | 1.0   | 121  | 5.2448          |
| 5.1711        | 2.0   | 242  | 5.3494          |
| 5.1571        | 3.0   | 363  | 5.4986          |
| 5.1536        | 4.0   | 484  | 5.7790          |


### Framework versions

- Transformers 4.46.3
- Pytorch 2.5.1+cpu
- Datasets 3.1.0
- Tokenizers 0.20.3