Downloads · 30 days
7
2% of all-time downloads
scibert_scivocab_uncased_NER_VISBank
Yamei/scibert_scivocab_uncased_NER_VISBank
scibert_scivocab_uncased_NER_VISBank is a token classification model from Yamei. 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
407
Public
Repo size
9.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin437 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Feb 23, 2023
- Updated
- Feb 24, 2023
- SHA
- 7ede96e2
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. -->
scibert_scivocab_uncased-v10-ES-ner
This model is a fine-tuned version of allenai/scibert_scivocab_uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4185
- Precision: 0.6897
- Recall: 0.7616
- F1: 0.7239
- Accuracy: 0.9263
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.3431 | 1.75 | 500 | 0.2748 | 0.6883 | 0.7114 | 0.6996 | 0.9210 |
| 0.1592 | 3.5 | 1000 | 0.3008 | 0.7108 | 0.7598 | 0.7345 | 0.9255 |
| 0.0891 | 5.24 | 1500 | 0.3634 | 0.6839 | 0.7132 | 0.6983 | 0.9214 |
| 0.0484 | 6.99 | 2000 | 0.3894 | 0.6831 | 0.7505 | 0.7152 | 0.9239 |
| 0.029 | 8.74 | 2500 | 0.4185 | 0.6897 | 0.7616 | 0.7239 | 0.9263 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.0
- Tokenizers 0.13.2
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- Created
- Feb 23, 2023
- Updated
- Feb 24, 2023