Downloads · 30 days
10
31% of all-time downloads
BioLinkBERT-base-drugtemist-en-fasttext-85-ner
Rodrigo1771/BioLinkBERT-base-drugtemist-en-fasttext-85-ner
BioLinkBERT-base-drugtemist-en-fasttext-85-ner is a token classification model from Rodrigo1771. 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
32
Public
Parameters
108M
4.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors431 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Sep 9, 2024
- Updated
- Sep 9, 2024
- SHA
- 81dae78e
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. -->
output
This model is a fine-tuned version of michiyasunaga/BioLinkBERT-base on the Rodrigo1771/drugtemist-en-fasttext-85-ner dataset. It achieves the following results on the evaluation set:
- Loss: 0.0077
- Precision: 0.925
- Recall: 0.9310
- F1: 0.9280
- Accuracy: 0.9987
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 448 | 0.0054 | 0.9404 | 0.8975 | 0.9185 | 0.9986 |
| 0.016 | 2.0 | 896 | 0.0045 | 0.9162 | 0.9171 | 0.9166 | 0.9986 |
| 0.0039 | 3.0 | 1344 | 0.0058 | 0.9064 | 0.9385 | 0.9222 | 0.9985 |
| 0.0022 | 4.0 | 1792 | 0.0057 | 0.8963 | 0.9348 | 0.9151 | 0.9985 |
| 0.0017 | 5.0 | 2240 | 0.0060 | 0.9178 | 0.9366 | 0.9271 | 0.9987 |
| 0.0012 | 6.0 | 2688 | 0.0063 | 0.9254 | 0.9254 | 0.9254 | 0.9987 |
| 0.0008 | 7.0 | 3136 | 0.0069 | 0.9130 | 0.9394 | 0.9260 | 0.9986 |
| 0.0005 | 8.0 | 3584 | 0.0069 | 0.9214 | 0.9292 | 0.9253 | 0.9986 |
| 0.0004 | 9.0 | 4032 | 0.0077 | 0.9249 | 0.9292 | 0.9270 | 0.9987 |
| 0.0004 | 10.0 | 4480 | 0.0077 | 0.925 | 0.9310 | 0.9280 | 0.9987 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Created
- Sep 9, 2024
- Updated
- Sep 9, 2024