---
license: mit
tags:
- generated_from_trainer
model-index:
- name: ukraine-clm
  results: []
language:
- de
widget:
- text: Selenskyj fordert sicheren Korridor für Getreidelieferungen
  example_title: Example 1
- text: Italien bestellt russischen Botschafter ein
  example_title: Example 2
- text: Lage in Sjewjerodonezk für Ukraine verschlechtert
  example_title: Example 3
datasets:
- pstuerner/ukraine-liveblog
---

<!-- 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. -->

# ukraine-clm

This model is a fine-tuned version of [dbmdz/german-gpt2](https://huggingface.co/dbmdz/german-gpt2) on the [ukraine-liveblog](https://huggingface.co/datasets/pstuerner/ukraine-liveblog) dataset.
It achieves the following results on the evaluation set:
- Loss: 2.7638

## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.7968        | 1.0   | 2109 | 2.8014          |
| 2.6909        | 2.0   | 4218 | 2.7699          |
| 2.643         | 3.0   | 6327 | 2.7638          |


### Framework versions

- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.0
- Tokenizers 0.13.2