---
license: llama3
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: hf_llama3_fft
  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/hmosousa/huggingface/runs/b807nfui)
# hf_llama3_fft

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 an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2394

## 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: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 64
- total_train_batch_size: 512
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.2075        | 0.2978 | 1000 | 1.2831          |
| 1.158         | 0.5957 | 2000 | 1.2598          |
| 1.1052        | 0.8935 | 3000 | 1.2394          |


### Framework versions

- Transformers 4.43.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1