metadata

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

ukraine-clm

This model is a fine-tuned version of dbmdz/german-gpt2 on the 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