Downloads · 30 days
18
27% of all-time downloads
distil-bert-docred-ner
dennishauser/distil-bert-docred-ner
distil-bert-docred-ner is a token classification model from dennishauser. 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
67
Public
Parameters
66.4M
266 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors266 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Nov 14, 2023
- Updated
- Nov 14, 2023
- SHA
- 008a9988
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. -->
distil-bert-docred-ner
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0744
- Precision: 0.8921
- Recall: 0.9081
- F1: 0.9000
- Accuracy: 0.9768
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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1325 | 1.0 | 1516 | 0.0923 | 0.8675 | 0.8903 | 0.8787 | 0.9712 |
| 0.0952 | 2.0 | 3032 | 0.0744 | 0.8921 | 0.9081 | 0.9000 | 0.9768 |
Framework versions
- Transformers 4.35.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Task
- Token Classification
- Library
- transformers
- Type
- distilbert
- License
- apache-2.0
- Created
- Nov 14, 2023
- Updated
- Nov 14, 2023