Downloads · 30 days
9
29% of all-time downloads
kien47/BPE_NER
BPE_NER is a token classification model from kien47. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
9
29% of all-time downloads
All-time downloads
31
Public
Repo size
3 GB
Likes
0
Public
Click a slice to open those files.
.bin496 MB · 99%
From the Hugging Face model README
This model is a fine-tuned version of FacebookAI/roberta-base on the conll2003 dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0787 | 1.0 | 1756 | 0.0554 | 0.9325 | 0.9507 | 0.9415 | 0.9867 |
| 0.0364 | 2.0 | 3512 | 0.0541 | 0.9446 | 0.9579 | 0.9512 | 0.9892 |
| 0.0213 | 3.0 | 5268 | 0.0561 | 0.9465 | 0.9579 | 0.9522 | 0.9892 |