Downloads · 30 days
12
23% of all-time downloads
clinical_keywords_ner_v1
imperiumhf/clinical_keywords_ner_v1
clinical_keywords_ner_v1 is a token classification model from imperiumhf. Use it when you need labels on individual words, such as names. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
53
Public
Parameters
148M
592 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors592 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- longformer
- Access
- Public
- Created
- Dec 19, 2023
- Updated
- Jan 11, 2024
- SHA
- 3432f4a1
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. -->
imp-mesh-ner
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0291
- Precision: 0.9719
- Recall: 0.9787
- F1: 0.9753
- Accuracy: 0.9972
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: 1
- eval_batch_size: 1
- 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 |
|---|---|---|---|---|---|---|---|
| 0.0159 | 1.0 | 10000 | 0.0262 | 0.9555 | 0.9619 | 0.9587 | 0.9958 |
| 0.0093 | 2.0 | 20000 | 0.0255 | 0.9631 | 0.9727 | 0.9679 | 0.9966 |
| 0.007 | 3.0 | 30000 | 0.0282 | 0.9662 | 0.9751 | 0.9706 | 0.9969 |
| 0.0058 | 4.0 | 40000 | 0.0326 | 0.9713 | 0.9785 | 0.9749 | 0.9972 |
| 0.0043 | 5.0 | 50000 | 0.0291 | 0.9719 | 0.9787 | 0.9753 | 0.9972 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Task
- Token Classification
- Library
- transformers
- Type
- longformer
- Created
- Dec 19, 2023
- Updated
- Jan 11, 2024