---
library_name: peft
base_model: tachiwin/pretrained_multilingual_instruct
tags:
- unsloth
- trl
- sft
- generated_from_trainer
model-index:
- name: multilingual
  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. -->

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/tachiwin/tachiwin_finetune/runs/ms960iob)
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/tachiwin/tachiwin_finetune/runs/ms960iob)
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/tachiwin/tachiwin_finetune/runs/ms960iob)
# multilingual

This model is a fine-tuned version of [tachiwin/pretrained_multilingual_instruct](https://huggingface.co/tachiwin/pretrained_multilingual_instruct) on an unknown dataset.

## 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: 3.224270650583368e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 3407
- gradient_accumulation_steps: 32
- total_train_batch_size: 1024
- optimizer: Use OptimizerNames.LION_8BIT and the args are:
No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 1

### Framework versions

- PEFT 0.15.2
- Transformers 4.51.3
- Pytorch 2.7.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1