Downloads · 30 days
33
4% of all-time downloads
IceBERT-finetuned-ner
vesteinn/IceBERT-finetuned-ner
IceBERT-finetuned-ner is a token classification model from vesteinn. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as gpl-3.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
846
Public
Parameters
124M
4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin496 MB · 50%
Parameter types
How the weights are stored.
F32124M · 100%
Try a prompt
Base models
Datasets
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. -->
IceBERT-finetuned-ner
This model is a fine-tuned version of vesteinn/IceBERT on the mim_gold_ner dataset. It achieves the following results on the evaluation set:
- Loss: 0.0815
- Precision: 0.8870
- Recall: 0.8576
- F1: 0.8721
- Accuracy: 0.9848
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.0536 | 1.0 | 2904 | 0.0749 | 0.8749 | 0.8426 | 0.8585 | 0.9831 |
| 0.0269 | 2.0 | 5808 | 0.0754 | 0.8734 | 0.8471 | 0.8600 | 0.9840 |
| 0.0173 | 3.0 | 8712 | 0.0815 | 0.8870 | 0.8576 | 0.8721 | 0.9848 |
Framework versions
- Transformers 4.11.0
- Pytorch 1.9.0+cu102
- Datasets 1.12.1
- Tokenizers 0.10.3
- Task
- Token Classification
- Library
- transformers
- Type
- roberta
- License
- gpl-3.0
- Created
- Mar 2, 2022
- Updated
- Feb 25, 2025