--- language: de license: mit tags: - flair - token-classification - sequence-tagger-model base_model: hmbyt5-preliminary/byt5-small-historic-multilingual-span20-flax inference: false widget: - text: Es war am 25sten , als Lord Corn wollis Dublin mit seinem Gefolge und mehrern Truppen verließ , um in einer Central - Lage bey Sligo die Operationen der Armee persönlich zu dirigiren . Der Feind dürfte bald in die Enge kommen , da Gen . Lacke mit 6000 Mann ihm entgegen marschirt . --- # Fine-tuned Flair Model on German HIPE-2020 Dataset (HIPE-2022) This Flair model was fine-tuned on the [German HIPE-2020](https://github.com/hipe-eval/HIPE-2022-data/blob/main/documentation/README-hipe2020.md) NER Dataset using hmByT5 as backbone LM. The HIPE-2020 dataset is comprised of newspapers from mid 19C to mid 20C. For information can be found [here](https://dl.acm.org/doi/abs/10.1007/978-3-030-58219-7_21). The following NEs were annotated: `loc`, `org`, `pers`, `prod`, `time` and `comp`. # ⚠️ Inference Widget ⚠️ Fine-Tuning ByT5 models in Flair is currently done by implementing an own [`ByT5Embedding`][0] class. This class needs to be present when running the model with Flair. Thus, the inference widget is not working with hmByT5 at the moment on the Model Hub and is currently disabled. This should be fixed in future, when ByT5 fine-tuning is supported in Flair directly. [0]: https://github.com/stefan-it/hmBench/blob/main/byt5_embeddings.py # Results We performed a hyper-parameter search over the following parameters with 5 different seeds per configuration: * Batch Sizes: `[8, 4]` * Learning Rates: `[0.00015, 0.00016]` And report micro F1-score on development set: | Configuration | Run 1 | Run 2 | Run 3 | Run 4 | Run 5 | Avg. | |-------------------|--------------|--------------|--------------|--------------|--------------|--------------| | bs4-e10-lr0.00016 | [0.7596][1] | [0.7466][2] | [0.7771][3] | [0.7894][4] | [0.7717][5] | 76.89 ± 1.47 | | bs8-e10-lr0.00015 | [0.7593][6] | [0.7663][7] | [0.7611][8] | [0.7647][9] | [0.7667][10] | 76.36 ± 0.29 | | bs8-e10-lr0.00016 | [0.7607][11] | [0.7736][12] | [0.7567][13] | [0.756][14] | [0.746][15] | 75.86 ± 0.89 | | bs4-e10-lr0.00015 | [0.7541][16] | [0.7466][17] | [0.7575][18] | [0.7579][19] | [0.7599][20] | 75.52 ± 0.47 | [1]: https://hf.co/stefan-it/hmbench-hipe2020-de-hmbyt5-bs4-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-1 [2]: https://hf.co/stefan-it/hmbench-hipe2020-de-hmbyt5-bs4-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-2 [3]: https://hf.co/stefan-it/hmbench-hipe2020-de-hmbyt5-bs4-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-3 [4]: https://hf.co/stefan-it/hmbench-hipe2020-de-hmbyt5-bs4-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-4 [5]: https://hf.co/stefan-it/hmbench-hipe2020-de-hmbyt5-bs4-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-5 [6]: https://hf.co/stefan-it/hmbench-hipe2020-de-hmbyt5-bs8-wsFalse-e10-lr0.00015-poolingfirst-layers-1-crfFalse-1 [7]: https://hf.co/stefan-it/hmbench-hipe2020-de-hmbyt5-bs8-wsFalse-e10-lr0.00015-poolingfirst-layers-1-crfFalse-2 [8]: https://hf.co/stefan-it/hmbench-hipe2020-de-hmbyt5-bs8-wsFalse-e10-lr0.00015-poolingfirst-layers-1-crfFalse-3 [9]: https://hf.co/stefan-it/hmbench-hipe2020-de-hmbyt5-bs8-wsFalse-e10-lr0.00015-poolingfirst-layers-1-crfFalse-4 [10]: https://hf.co/stefan-it/hmbench-hipe2020-de-hmbyt5-bs8-wsFalse-e10-lr0.00015-poolingfirst-layers-1-crfFalse-5 [11]: https://hf.co/stefan-it/hmbench-hipe2020-de-hmbyt5-bs8-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-1 [12]: https://hf.co/stefan-it/hmbench-hipe2020-de-hmbyt5-bs8-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-2 [13]: https://hf.co/stefan-it/hmbench-hipe2020-de-hmbyt5-bs8-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-3 [14]: https://hf.co/stefan-it/hmbench-hipe2020-de-hmbyt5-bs8-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-4 [15]: https://hf.co/stefan-it/hmbench-hipe2020-de-hmbyt5-bs8-wsFalse-e10-lr0.00016-poolingfirst-layers-1-crfFalse-5 [16]: https://hf.co/stefan-it/hmbench-hipe2020-de-hmbyt5-bs4-wsFalse-e10-lr0.00015-poolingfirst-layers-1-crfFalse-1 [17]: https://hf.co/stefan-it/hmbench-hipe2020-de-hmbyt5-bs4-wsFalse-e10-lr0.00015-poolingfirst-layers-1-crfFalse-2 [18]: https://hf.co/stefan-it/hmbench-hipe2020-de-hmbyt5-bs4-wsFalse-e10-lr0.00015-poolingfirst-layers-1-crfFalse-3 [19]: https://hf.co/stefan-it/hmbench-hipe2020-de-hmbyt5-bs4-wsFalse-e10-lr0.00015-poolingfirst-layers-1-crfFalse-4 [20]: https://hf.co/stefan-it/hmbench-hipe2020-de-hmbyt5-bs4-wsFalse-e10-lr0.00015-poolingfirst-layers-1-crfFalse-5 The [training log](training.log) and TensorBoard logs (only for hmByT5 and hmTEAMS based models) are also uploaded to the model hub. More information about fine-tuning can be found [here](https://github.com/stefan-it/hmBench). # Acknowledgements We thank [Luisa März](https://github.com/LuisaMaerz), [Katharina Schmid](https://github.com/schmika) and [Erion Çano](https://github.com/erionc) for their fruitful discussions about Historic Language Models. Research supported with Cloud TPUs from Google's [TPU Research Cloud](https://sites.research.google/trc/about/) (TRC). Many Thanks for providing access to the TPUs ❤️