Downloads · 30 days
41
4% of all-time downloads
amichailidis/bert-base-greek-uncased-v1-finetuned-ner
bert-base-greek-uncased-v1-finetuned-ner is a token classification model from amichailidis. Use it when you need labels on individual words, such as names. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
41
4% of all-time downloads
All-time downloads
1K
Public
Repo size
899 MB
Likes
0
Public
Click a slice to open those files.
.bin449 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of nlpaueb/bert-base-greek-uncased-v1 on an unknown 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 |
|---|---|---|---|---|---|---|---|
| No log | 0.64 | 250 | 0.0913 | 0.7814 | 0.8208 | 0.8073 | 0.9728 |
| 0.1144 | 1.29 | 500 | 0.0823 | 0.7940 | 0.8448 | 0.8342 | 0.9755 |
| 0.1144 | 1.93 | 750 | 0.0812 | 0.8057 | 0.8212 | 0.8328 | 0.9751 |
| 0.0570 | 2.58 | 1000 | 0.0855 | 0.8244 | 0.8514 | 0.8292 | 0.9744 |
| 0.0570 | 3.22 | 1250 | 0.0926 | 0.8329 | 0.8441 | 0.8397 | 0.9760 |
| 0.0393 | 3.87 | 1500 | 0.0869 | 0.8256 | 0.8633 | 0.8440 | 0.9774 |
| 0.0393 | 4.51 | 1750 | 0.1049 | 0.8290 | 0.8636 | 0.8459 | 0.9766 |
| 0.026 | 5.15 | 2000 | 0.1093 | 0.8440 | 0.8566 | 0.8503 | 0.9768 |
| 0.026 | 5.8 | 2250 | 0.1172 | 0.8301 | 0.8514 | 0.8406 | 0.9760 |
| 0.0189 | 6.44 | 2500 | 0.1273 | 0.8238 | 0.8688 | 0.8457 | 0.9766 |
| 0.0189 | 7.09 | 2750 | 0.1246 | 0.8350 | 0.8539 | 0.8443 | 0.9764 |
| 0.0148 | 7.73 | 3000 | 0.1262 | 0.8333 | 0.8608 | 0.8468 | 0.9764 |
| 0.0148 | 8.38 | 3250 | 0.1347 | 0.8319 | 0.8591 | 0.8453 | 0.9762 |
| 0.0010 | 9.02 | 3500 | 0.1325 | 0.8376 | 0.8504 | 0.8439 | 0.9766 |
| 0.0010 | 9.66 | 3750 | 0.1362 | 0.8371 | 0.8563 | 0.8466 | 0.9765 |