Downloads · 30 days
14
3% of all-time downloads
bge-finetuned-ner
maratgalyavov/bge-finetuned-ner
bge-finetuned-ner is a token classification model from maratgalyavov. 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. --
All-time downloads
452
Public
Parameters
33.2M
17.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt266 MB · 50%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- mit
- Model type
- bert
- Access
- Public
- Created
- Oct 8, 2025
- Updated
- Oct 14, 2025
- SHA
- 61917e01
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
bge-finetuned-ner
This model is a fine-tuned version of BAAI/bge-small-en-v1.5 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0827
- Precision: 0.9125
- Recall: 0.9305
- F1: 0.9214
- Accuracy: 0.9831
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2101 | 1.0 | 626 | 0.1545 | 0.7855 | 0.8270 | 0.8057 | 0.9626 |
| 0.0968 | 2.0 | 1252 | 0.0966 | 0.8584 | 0.9098 | 0.8833 | 0.9762 |
| 0.076 | 3.0 | 1878 | 0.0822 | 0.9011 | 0.9123 | 0.9067 | 0.9799 |
| 0.0392 | 4.0 | 2504 | 0.0787 | 0.8992 | 0.9216 | 0.9102 | 0.9810 |
| 0.0257 | 5.0 | 3130 | 0.0812 | 0.8941 | 0.9249 | 0.9093 | 0.9807 |
| 0.0242 | 6.0 | 3756 | 0.0800 | 0.9029 | 0.9283 | 0.9154 | 0.9817 |
| 0.0115 | 7.0 | 4382 | 0.0799 | 0.9056 | 0.9278 | 0.9165 | 0.9824 |
| 0.0159 | 8.0 | 5008 | 0.0827 | 0.9125 | 0.9305 | 0.9214 | 0.9831 |
| 0.0145 | 9.0 | 5634 | 0.0840 | 0.9133 | 0.9288 | 0.9210 | 0.9833 |
| 0.0086 | 10.0 | 6260 | 0.0851 | 0.9125 | 0.9290 | 0.9207 | 0.9830 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.8.0+cu126
- Datasets 3.4.1
- Tokenizers 0.21.4
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- mit
- Created
- Oct 8, 2025
- Updated
- Oct 14, 2025