---
license: llama3.1
datasets:
- trollek/Danoia-v03
- trollek/Danoia-v02
- N8Programs/CreativeGPT
- Gryphe/Opus-WritingPrompts
language:
- da
- en
base_model:
- unsloth/Meta-Llama-3.1-8B-Instruct
library_name: transformers
tags:
- llama-factory
- unsloth
---
# Llama 3.1 8B Danoia

This model is a fine-tuned version of [unsloth/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct) on the danoia_v03, the opus_writing_instruct, the creativegpt and the danoia_v02_no_system datasets + some private datasets related to evaluation.

It achieves the following results on the evaluation set:
- Loss: 0.7108

## Model description

This model can write stories in danish and english. It can do much more, I am sure of it, but not more than the vanilla model it is based on.

## Intended uses & limitations

Danoia is intended to be private assistant able to write essays, summarise articles, and be a helpful assistant in general. It misspells danish words at times but it is rare though.

## Training and evaluation data

I trained this using [LLama-Factory](https://github.com/hiyouga/LLaMA-Factory "LLama Factorys' GitHub") with [unsloth](https://github.com/unslothai/unsloth "unsloths' GitHub") enabled on a 16GB 4060 Ti. It took 30 hours and peaked at 13GB VRAM usage. 

<details>
  
  <summary>Show LLama-Factory config</summary>
  
```yaml
### model
model_name_or_path: unsloth/Meta-Llama-3.1-8B-Instruct

### method
stage: sft
do_train: true
finetuning_type: lora
lora_target: all
loraplus_lr_ratio: 16.0
lora_rank: 16
lora_alpha: 32
use_unsloth: true
use_unsloth_gc: true
quantization_bit: 4
upcast_layernorm: true
seed: 192

### dataset
dataset: danoia_v03,opus_writing_instruct,creativegpt,danoia_v02_no_system
template: llama3
cutoff_len: 8192
overwrite_cache: false
preprocessing_num_workers: 12

### output
output_dir: llama31/8b_instruct/loras/danoia
logging_steps: 1
save_steps: 500
save_strategy: steps
plot_loss: true
overwrite_output_dir: false

### train
per_device_train_batch_size: 2
gradient_accumulation_steps: 4
learning_rate: 1.5e-5
num_train_epochs: 1.5
lr_scheduler_type: cosine
warmup_ratio: 0.01
bf16: true

## eval
val_size: 0.01
per_device_eval_batch_size: 1
eval_strategy: steps
eval_steps: 500
```
</details>

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 1.5e-05
- train_batch_size: 2
- eval_batch_size: 1
- seed: 192
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 1.5

### Training results

| Training Loss | Epoch  | Step  | Validation Loss |
|:-------------:|:------:|:-----:|:---------------:|
| 0.2352        | 0.0719 | 500   | 0.8450          |
| 0.1742        | 0.1438 | 1000  | 0.8090          |
| 0.1667        | 0.2156 | 1500  | 0.7889          |
| 0.3791        | 0.2875 | 2000  | 0.7750          |
| 0.1989        | 0.3594 | 2500  | 0.7665          |
| 0.2347        | 0.4313 | 3000  | 0.7563          |
| 0.1694        | 0.5032 | 3500  | 0.7498          |
| 0.2351        | 0.5750 | 4000  | 0.7412          |
| 0.2322        | 0.6469 | 4500  | 0.7363          |
| 0.1689        | 0.7188 | 5000  | 0.7298          |
| 0.1953        | 0.7907 | 5500  | 0.7250          |
| 0.2099        | 0.8626 | 6000  | 0.7214          |
| 0.2368        | 0.9344 | 6500  | 0.7166          |
| 0.1632        | 1.0063 | 7000  | 0.7151          |
| 0.1558        | 1.0782 | 7500  | 0.7157          |
| 0.2854        | 1.1501 | 8000  | 0.7139          |
| 0.199         | 1.2220 | 8500  | 0.7127          |
| 0.1606        | 1.2938 | 9000  | 0.7117          |
| 0.1788        | 1.3657 | 9500  | 0.7112          |
| 0.2618        | 1.4376 | 10000 | 0.7109          |


### Framework versions

- PEFT 0.12.0
- Transformers 4.46.1
- Pytorch 2.5.1
- Datasets 3.1.0
- Tokenizers 0.20.3