Downloads · 30 days
2
8% of all-time downloads
hmbench-ajmc-en-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4
stefan-it/hmbench-ajmc-en-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4
hmbench-ajmc-en-hmteams-bs8-wsFalse-e10-lr3e-05-poolingfirst-layers-1-crfFalse-4 is a token classification model from stefan-it. Use it when you need labels on individual words, such as names. It is set up for flair. The card lists the license as mit.
This Flair model was fine-tuned on the AjMC English NER Dataset using hmTEAMS as backbone LM.
All-time downloads
24
Public
Repo size
441 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin441 MB · 100%
At a glance
- Task
- Token Classification
- Library
- flair
- License
- mit
- Access
- Public
- Created
- Oct 17, 2023
- Updated
- Oct 17, 2023
- SHA
- 6d428d5f
Try a prompt
Base models
Model card
From the Hugging Face model README
Fine-tuned Flair Model on AjMC English NER Dataset (HIPE-2022)
This Flair model was fine-tuned on the AjMC English NER Dataset using hmTEAMS 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 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:
[8, 4] - Learning Rates:
[3e-05, 5e-05]
And report micro F1-score on development set:
| Configuration | Run 1 | Run 2 | Run 3 | Run 4 | Run 5 | Avg. |
|---|---|---|---|---|---|---|
| bs4-e10-lr3e-05 | 0.8606 | 0.8657 | 0.8612 | 0.8609 | 0.8623 | 86.21 ± 0.19 |
| bs8-e10-lr3e-05 | 0.8479 | 0.8698 | 0.8613 | 0.8602 | 0.8588 | 85.96 ± 0.7 |
| bs8-e10-lr5e-05 | 0.8547 | 0.8558 | 0.8568 | 0.865 | 0.8633 | 85.91 ± 0.42 |
| bs4-e10-lr5e-05 | 0.8571 | 0.8432 | 0.8595 | 0.8656 | 0.8455 | 85.42 ± 0.85 |
The 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.
Acknowledgements
We thank Luisa März, Katharina Schmid and Erion Çano for their fruitful discussions about Historic Language Models.
Research supported with Cloud TPUs from Google's TPU Research Cloud (TRC). Many Thanks for providing access to the TPUs ❤️
- Task
- Token Classification
- Library
- flair
- License
- mit
- Languages
- en
- Created
- Oct 17, 2023
- Updated
- Oct 17, 2023