README.md

---
base_model: meta-llama/Llama-3.2-1B-Instruct
datasets:
- generator
library_name: peft
license: llama3.2
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Llama-3.2-1B-Indonesian
  results: []
language:
- id
pipeline_tag: text-generation
---

<!-- 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. -->

# Llama-3.2-1B-Indonesian

This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) that has been optimized for Indonesian language understanding and generation..

## Training and evaluation data

[Ichsan2895/alpaca-gpt4-indonesian](https://huggingface.co/datasets/Ichsan2895/alpaca-gpt4-indonesian)

### Use WIth Transformers
```python
import torch
from transformers import pipeline

model_id = "meta-llama/Llama-3.2-3B-Instruct"
pipe = pipeline(
    "text-generation",
    model=model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]
outputs = pipe(
    messages,
    max_new_tokens=256,
)
print(outputs[0]["generated_text"][-1])
```

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 6
- total_train_batch_size: 6
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results
![Train Loss]
<img src="./train_loss.svg" width="300" height="200">

### Framework versions

- PEFT 0.7.2.dev0
- Transformers 4.46.1
- Pytorch 2.4.0+cu121
- Datasets 2.16.1
- Tokenizers 0.20.1