---
license: other
base_model: Ai-Sweden-Models/gpt-sw3-126m
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: gpt-sw3-126m-nqii-ruqad
  results: []
datasets:
- Sigurdur/nqii_ruqad
language:
- is
- da
- sv
- en
- 'no'
library_name: transformers
pipeline_tag: text-generation
---

[<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/sigurdurhaukur-team/huggingface/runs/i9i7wb82)
# gpt-sw3-126m-nqii-ruqad

This model is a fine-tuned version of [Ai-Sweden-Models/gpt-sw3-126m](https://huggingface.co/Ai-Sweden-Models/gpt-sw3-126m) on [Sigurdur/nqii_ruqad](https://huggingface.co/Sigurdur/nqii_ruqad)

## Model description

The model has been finetuned to answer questions in the following format

```
### Question: <your question>
```

It will then answer in the following manner:

```
### Answer: <model answer>
```


## 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: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1

### Training results



### Framework versions

- Transformers 4.42.3
- Pytorch 2.1.2+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1