---
base_model: meta-llama/Llama-3.2-3B
library_name: peft
license: mit
tags:
- generated_from_trainer
model-index:
- name: llama3.2-finetuned
  results: []
datasets:
- ashuwhy/poplyrics-1k
---

<!-- 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. -->

# llama3.2-poplyrics-1k

This model is a fine-tuned version of [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B) on my dataset [ashuwhy/poplyrics-1k](https://huggingface.co/alexshcer/poplyrics-1k).
It achieves the following results on the evaluation set:
- Loss: 1.4958

## Model description

It generate pop lyrics.

## Intended uses & limitations

For generating pop lyrics, it generates trashy lyrics.

## Training and evaluation data

Later, more training needed.

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.4989        | 1.1111 | 500  | 1.5091          |
| 1.6184        | 2.2222 | 1000 | 1.4958          |


### Framework versions

- PEFT 0.13.2
- Transformers 4.45.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.1