stefan-it's picture
readme: add initial version of model card (#1)
ed3fff4
---
language: fr
license: mit
tags:
- flair
- token-classification
- sequence-tagger-model
base_model: dbmdz/bert-base-historic-multilingual-64k-td-cased
widget:
- text: 469 . Πεδία . Les tribraques formés par un seul mot sont rares chez les
tragiques , partont ailleurs qu au premier pied . . cependant QEd , Roi ,
719 , 826 , 4496 .
---
# Fine-tuned Flair Model on AjMC French NER Dataset (HIPE-2022)
This Flair model was fine-tuned on the
[AjMC French](https://github.com/hipe-eval/HIPE-2022-data/blob/main/documentation/README-ajmc.md)
NER Dataset using hmBERT 64k as backbone LM.
The AjMC dataset consists of NE-annotated historical commentaries in the field of Classics,
and was created in the context of the [Ajax MultiCommentary](https://mromanello.github.io/ajax-multi-commentary/)
project.
The following NEs were annotated: `pers`, `work`, `loc`, `object`, `date` and `scope`.
# Results
We performed a hyper-parameter search over the following parameters with 5 different seeds per configuration:
* Batch Sizes: `[4, 8]`
* Learning Rates: `[3e-05, 5e-05]`
And report micro F1-score on development set:
| Configuration | Seed 1 | Seed 2 | Seed 3 | Seed 4 | Seed 5 | Average |
|-------------------|--------------|------------------|--------------|--------------|--------------|-----------------|
| `bs4-e10-lr3e-05` | [0.8586][1] | [0.8586][2] | [0.8688][3] | [0.8539][4] | [0.8529][5] | 0.8586 ± 0.0063 |
| `bs8-e10-lr5e-05` | [0.8539][6] | [0.8653][7] | [0.8518][8] | [0.8536][9] | [0.8374][10] | 0.8524 ± 0.0099 |
| `bs8-e10-lr3e-05` | [0.8486][11] | [0.8486][12] | [0.8522][13] | [0.8512][14] | [0.8414][15] | 0.8484 ± 0.0042 |
| `bs4-e10-lr5e-05` | [0.8529][16] | [**0.8425**][17] | [0.8501][18] | [0.8412][19] | [0.8501][20] | 0.8474 ± 0.0052 |
[1]: https://hf.co/stefan-it/hmbench-ajmc-fr-hmbert_64k-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1
[2]: https://hf.co/stefan-it/hmbench-ajmc-fr-hmbert_64k-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2
[3]: https://hf.co/stefan-it/hmbench-ajmc-fr-hmbert_64k-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3
[4]: https://hf.co/stefan-it/hmbench-ajmc-fr-hmbert_64k-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4
[5]: https://hf.co/stefan-it/hmbench-ajmc-fr-hmbert_64k-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5
[6]: https://hf.co/stefan-it/hmbench-ajmc-fr-hmbert_64k-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1
[7]: https://hf.co/stefan-it/hmbench-ajmc-fr-hmbert_64k-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2
[8]: https://hf.co/stefan-it/hmbench-ajmc-fr-hmbert_64k-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3
[9]: https://hf.co/stefan-it/hmbench-ajmc-fr-hmbert_64k-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4
[10]: https://hf.co/stefan-it/hmbench-ajmc-fr-hmbert_64k-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5
[11]: https://hf.co/stefan-it/hmbench-ajmc-fr-hmbert_64k-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1
[12]: https://hf.co/stefan-it/hmbench-ajmc-fr-hmbert_64k-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2
[13]: https://hf.co/stefan-it/hmbench-ajmc-fr-hmbert_64k-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3
[14]: https://hf.co/stefan-it/hmbench-ajmc-fr-hmbert_64k-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4
[15]: https://hf.co/stefan-it/hmbench-ajmc-fr-hmbert_64k-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5
[16]: https://hf.co/stefan-it/hmbench-ajmc-fr-hmbert_64k-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1
[17]: https://hf.co/stefan-it/hmbench-ajmc-fr-hmbert_64k-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2
[18]: https://hf.co/stefan-it/hmbench-ajmc-fr-hmbert_64k-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3
[19]: https://hf.co/stefan-it/hmbench-ajmc-fr-hmbert_64k-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4
[20]: https://hf.co/stefan-it/hmbench-ajmc-fr-hmbert_64k-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5
The [training log](training.log) and TensorBoard logs (not available for hmBERT Base model) 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 ❤️