Downloads · 30 days
13
3% of all-time downloads
bert-base-uncased-finetuned-ner
deval/bert-base-uncased-finetuned-ner
bert-base-uncased-finetuned-ner is a token classification model from deval. 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. --
All-time downloads
517
Public
Repo size
871 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin436 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Sep 21, 2021
- SHA
- 4bc297ca
Try a prompt
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. -->
bert-base-uncased-finetuned-ner
This model is a fine-tuned version of bert-base-uncased on the x_glue dataset. It achieves the following results on the evaluation set:
- Loss: 2.7979
- Precision: 0.0919
- Recall: 0.1249
- F1: 0.1059
- Accuracy: 0.4927
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1773 | 1.0 | 878 | 1.7953 | 0.1025 | 0.1352 | 0.1166 | 0.5058 |
| 0.0397 | 2.0 | 1756 | 2.0827 | 0.0906 | 0.1230 | 0.1043 | 0.4888 |
| 0.022 | 3.0 | 2634 | 2.8677 | 0.0864 | 0.1260 | 0.1025 | 0.4098 |
| 0.0126 | 4.0 | 3512 | 2.8584 | 0.0848 | 0.1201 | 0.0994 | 0.4424 |
| 0.0085 | 5.0 | 4390 | 2.7979 | 0.0919 | 0.1249 | 0.1059 | 0.4927 |
Framework versions
- Transformers 4.10.2
- Pytorch 1.9.0+cu102
- Datasets 1.12.1
- Tokenizers 0.10.3
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Mar 2, 2022
- Updated
- Sep 21, 2021