---
library_name: transformers
license: llama3
base_model: ytu-ce-cosmos/Turkish-Llama-8b-v0.1
tags:
- generated_from_trainer
model-index:
- name: turkish-llama-MSFT-0.7
  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. -->

# turkish-llama-MSFT-0.7

This model is a fine-tuned version of [ytu-ce-cosmos/Turkish-Llama-8b-v0.1](https://huggingface.co/ytu-ce-cosmos/Turkish-Llama-8b-v0.1) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3326

## 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: 2
- eval_batch_size: 8
- seed: 46
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 0.03
- num_epochs: 2

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.4866        | 0.4921 | 90   | 0.4801          |
| 0.3473        | 0.9843 | 180  | 0.3459          |
| 0.2589        | 1.4757 | 270  | 0.3362          |
| 0.2526        | 1.9679 | 360  | 0.3326          |


### Framework versions

- Transformers 5.3.0
- Pytorch 2.10.0+cu128
- Datasets 4.8.4
- Tokenizers 0.22.2