Downloads · 30 days
2
5% of all-time downloads
biogpt-ncbi-disease-ner
HungsingWong/biogpt-ncbi-disease-ner
biogpt-ncbi-disease-ner is a machine learning model from HungsingWong. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
should probably proofread and complete it, then remove this comment. --
All-time downloads
43
Public
Parameters
347M
1.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.4 GB · 100%
At a glance
- Model type
- gpt2
- Access
- Public
- Created
- Apr 4, 2026
- Updated
- Apr 4, 2026
- SHA
- 8d9a6b67
Datasets
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. -->
biogpt-ncbi-disease-ner
This model was trained from scratch on the ncbi_disease dataset. It achieves the following results on the evaluation set:
- Loss: 0.2796
- Precision: 0.5711
- Recall: 0.6062
- F1: 0.5882
- Accuracy: 0.9559
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1798 | 1.0 | 680 | 0.2421 | 0.1967 | 0.5057 | 0.2833 | 0.9123 |
| 0.1468 | 2.0 | 1360 | 0.1426 | 0.4127 | 0.5044 | 0.4540 | 0.9564 |
| 0.117 | 3.0 | 2040 | 0.1507 | 0.4774 | 0.5375 | 0.5057 | 0.9603 |
| 0.0664 | 4.0 | 2720 | 0.1913 | 0.4904 | 0.5184 | 0.5040 | 0.9611 |
| 0.0621 | 5.0 | 3400 | 0.1507 | 0.5117 | 0.5845 | 0.5457 | 0.9627 |
| 0.0372 | 6.0 | 4080 | 0.2094 | 0.5267 | 0.5756 | 0.5501 | 0.9620 |
| 0.0278 | 7.0 | 4760 | 0.2052 | 0.5184 | 0.6074 | 0.5594 | 0.9617 |
| 0.025 | 8.0 | 5440 | 0.2023 | 0.5303 | 0.6010 | 0.5634 | 0.9611 |
| 0.0203 | 9.0 | 6120 | 0.2550 | 0.5354 | 0.6150 | 0.5724 | 0.9625 |
| 0.0133 | 10.0 | 6800 | 0.2511 | 0.5279 | 0.6125 | 0.5671 | 0.9612 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.3.1+cu121
- Datasets 3.6.0
- Tokenizers 0.19.1
- Type
- gpt2
- Created
- Apr 4, 2026
- Updated
- Apr 4, 2026