Downloads · 30 days
37
0% of all-time downloads
yanekyuk/bert-keyword-extractor
bert-keyword-extractor is a token classification model from yanekyuk. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
37
0% of all-time downloads
All-time downloads
29.8K
Public
Repo size
1.3 GB
Likes
49
Public
Click a slice to open those files.
.bin431 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of bert-base-cased 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 | Accuracy | F1 |
|---|---|---|---|---|---|---|---|
| 0.1688 | 1.0 | 1875 | 0.1233 | 0.7194 | 0.7738 | 0.9501 | 0.7456 |
| 0.1219 | 2.0 | 3750 | 0.1014 | 0.7724 | 0.8166 | 0.9606 | 0.7939 |
| 0.0834 | 3.0 | 5625 | 0.0977 | 0.8280 | 0.8263 | 0.9672 | 0.8272 |
| 0.0597 | 4.0 | 7500 | 0.0984 | 0.8304 | 0.8680 | 0.9704 | 0.8488 |
| 0.0419 | 5.0 | 9375 | 0.1042 | 0.8417 | 0.8687 | 0.9717 | 0.8550 |
| 0.0315 | 6.0 | 11250 | 0.1161 | 0.8520 | 0.8839 | 0.9729 | 0.8677 |
| 0.0229 | 7.0 | 13125 | 0.1282 | 0.8469 | 0.8939 | 0.9734 | 0.8698 |
| 0.0182 | 8.0 | 15000 | 0.1341 | 0.8565 | 0.8874 | 0.9738 | 0.8717 |