Downloads · 30 days
7
2% of all-time downloads
NER-CoNLL2003-V4
Xiaoman/NER-CoNLL2003-V4
NER-CoNLL2003-V4 is a token classification model from Xiaoman. 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
432
Public
Repo size
4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.3 GB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- May 14, 2022
- Updated
- May 14, 2022
- SHA
- 8a71c882
Try a prompt
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. -->
NER-CoNLL2003-V4
This model is a fine-tuned version of bert-large-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2095
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: 7.961395091713594e-05
- train_batch_size: 6
- eval_batch_size: 6
- seed: 27
- 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 |
|---|---|---|---|
| No log | 1.0 | 14 | 0.3630 |
| No log | 2.0 | 28 | 0.2711 |
| No log | 3.0 | 42 | 0.2407 |
| No log | 4.0 | 56 | 0.2057 |
| No log | 5.0 | 70 | 0.2095 |
Framework versions
- Transformers 4.19.1
- Pytorch 1.11.0+cu113
- Datasets 2.2.1
- Tokenizers 0.12.1
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- May 14, 2022
- Updated
- May 14, 2022