---
language: en
license: mit
tags:
- flair
- token-classification
- sequence-tagger-model
base_model: dbmdz/bert-base-historic-multilingual-64k-td-cased
widget:
- text: Cp . Eur . Phoen . 240 , 1 , αἷμα ddiov φλέγέι .
---

# Fine-tuned Flair Model on AjMC English NER Dataset (HIPE-2022)

This Flair model was fine-tuned on the
[AjMC English](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` | [0.8565][1]  | [0.8592][2]  | [0.8513][3]  | [**0.8622**][4] | [0.8534][5]  | 0.8565 ± 0.0044 |
| `bs4-e10-lr5e-05` | [0.8582][6]  | [0.852][7]   | [0.8517][8]  | [0.8544][9]     | [0.842][10]  | 0.8517 ± 0.006  |
| `bs8-e10-lr5e-05` | [0.8412][11] | [0.8369][12] | [0.853][13]  | [0.8392][14]    | [0.85][15]   | 0.8441 ± 0.007  |
| `bs8-e10-lr3e-05` | [0.8483][16] | [0.8431][17] | [0.8443][18] | [0.8486][19]    | [0.8359][20] | 0.844 ± 0.0052  |

[1]: https://hf.co/stefan-it/hmbench-ajmc-en-hmbert_64k-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1
[2]: https://hf.co/stefan-it/hmbench-ajmc-en-hmbert_64k-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2
[3]: https://hf.co/stefan-it/hmbench-ajmc-en-hmbert_64k-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3
[4]: https://hf.co/stefan-it/hmbench-ajmc-en-hmbert_64k-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4
[5]: https://hf.co/stefan-it/hmbench-ajmc-en-hmbert_64k-bs4-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-5
[6]: https://hf.co/stefan-it/hmbench-ajmc-en-hmbert_64k-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1
[7]: https://hf.co/stefan-it/hmbench-ajmc-en-hmbert_64k-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2
[8]: https://hf.co/stefan-it/hmbench-ajmc-en-hmbert_64k-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3
[9]: https://hf.co/stefan-it/hmbench-ajmc-en-hmbert_64k-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4
[10]: https://hf.co/stefan-it/hmbench-ajmc-en-hmbert_64k-bs4-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5
[11]: https://hf.co/stefan-it/hmbench-ajmc-en-hmbert_64k-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-1
[12]: https://hf.co/stefan-it/hmbench-ajmc-en-hmbert_64k-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-2
[13]: https://hf.co/stefan-it/hmbench-ajmc-en-hmbert_64k-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-3
[14]: https://hf.co/stefan-it/hmbench-ajmc-en-hmbert_64k-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-4
[15]: https://hf.co/stefan-it/hmbench-ajmc-en-hmbert_64k-bs8-wsFalse-e10-lr5e-05-poolingfirst-layers-1-crfFalse-5
[16]: https://hf.co/stefan-it/hmbench-ajmc-en-hmbert_64k-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-1
[17]: https://hf.co/stefan-it/hmbench-ajmc-en-hmbert_64k-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-2
[18]: https://hf.co/stefan-it/hmbench-ajmc-en-hmbert_64k-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-3
[19]: https://hf.co/stefan-it/hmbench-ajmc-en-hmbert_64k-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4
[20]: https://hf.co/stefan-it/hmbench-ajmc-en-hmbert_64k-bs8-wsFalse-e10-lr3e-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 ❤️