---
license: mit
base_model: microsoft/phi-2
tags:
- trl
- fietje
- alignment-handbook
datasets:
- uonlp/CulturaX
- wikimedia/wikipedia
model-index:
- name: fietje-2b
  results: []
language:
- nl
pipeline_tag: text-generation
inference: false
---


<p align="center" style="margin:0;padding:0">
  <img src="https://huggingface.co/BramVanroy/fietje-2b/resolve/main/img/fietje-2b-banner.png" alt="Fietje banner" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
</p>

<div style="margin:auto; text-align:center">
  <h1 style="margin-bottom: 0">Fietje 2B</h1>
  <em>An open and efficient LLM for Dutch</em>
</div>

<blockquote class="tip">
  <p align="center">
    <a rel="nofollow" href="https://huggingface.co/BramVanroy/fietje-2b">👱‍♀️ Base version</a> (this one) -
    <a rel="nofollow" href="https://huggingface.co/BramVanroy/fietje-2b-instruct">🤖 Instruct version</a> -
    <a rel="nofollow" href="https://huggingface.co/BramVanroy/fietje-2b-chat">💬 Chat version</a> -
    <a rel="nofollow" href="https://huggingface.co/BramVanroy/fietje-2b-GGUF">🚀 GGUF of base model</a>
  </p>
</blockquote>



This model is an adapted version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2), finetuned for Dutch text generation. It was continue-pretrained on 28B Dutch tokens, which includes the full Dutch component of Wikipedia (accounting for around 15%), supplemented with Dutch tokens from CulturaX. A newer version of this dataset can be found [here](https://huggingface.co/datasets/BramVanroy/wikipedia_culturax_dutch), which also describes the filtering that took place.

## 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: 9e-05
- train_batch_size: 40
- eval_batch_size: 40
- seed: 42
- distributed_type: multi-GPU
- num_devices: 16
- gradient_accumulation_steps: 3
- total_train_batch_size: 1920
- total_eval_batch_size: 640
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-07
- lr_scheduler_type: linear
- num_epochs: 1.0

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.6334        | 0.13  | 900  | 1.5937          |
| 1.5469        | 0.26  | 1800 | 1.5051          |
| 1.4937        | 0.4   | 2700 | 1.4628          |
| 1.4633        | 0.53  | 3600 | 1.4375          |
| 1.4485        | 0.66  | 4500 | 1.4203          |
| 1.4374        | 0.79  | 5400 | 1.4085          |
| 1.4278        | 0.92  | 6300 | 1.4013          |


### Framework versions

- Transformers 4.39.1
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2