---
base_model: meta-llama/Meta-Llama-3-8B-Instruct
library_name: peft
license: llama3
tags:
- generated_from_trainer
model-index:
- name: pgd_llama3_16bits_lr0.0002_alpha32_rk4_do0.1_wd1.0e-02
  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. -->

# pgd_llama3_16bits_lr0.0002_alpha32_rk4_do0.1_wd1.0e-02

This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9498

## 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: 0.0002
- train_batch_size: 3
- eval_batch_size: 3
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 12
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 2.2412        | 0.9867 | 37   | 1.0043          |
| 0.9676        | 2.0    | 75   | 0.9525          |
| 0.9473        | 2.9867 | 112  | 0.9120          |
| 0.8898        | 4.0    | 150  | 0.9089          |
| 0.9026        | 4.9867 | 187  | 0.9108          |
| 0.8704        | 6.0    | 225  | 0.9143          |
| 0.8839        | 6.9867 | 262  | 0.9186          |
| 0.8483        | 8.0    | 300  | 0.9278          |
| 0.8532        | 8.9867 | 337  | 0.9429          |
| 0.8142        | 9.8667 | 370  | 0.9498          |


### Framework versions

- PEFT 0.12.0
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1