Downloads · 30 days
6
19% of all-time downloads
biogpt
ywu289/biogpt
biogpt is a token classification model from ywu289. 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
31
Public
Parameters
347M
12.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.4 GB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- Model type
- gpt2
- Access
- Public
- Created
- Apr 12, 2024
- Updated
- Apr 14, 2024
- SHA
- 2421b964
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. -->
biogpt
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1404
- Precision: 0.4590
- Recall: 0.5400
- F1: 0.4962
- Accuracy: 0.9579
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
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.3225 | 1.0 | 679 | 0.1673 | 0.3285 | 0.4041 | 0.3624 | 0.9473 |
| 0.1696 | 2.0 | 1358 | 0.1510 | 0.4053 | 0.5464 | 0.4654 | 0.9532 |
| 0.0986 | 3.0 | 2037 | 0.1404 | 0.4590 | 0.5400 | 0.4962 | 0.9579 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Task
- Token Classification
- Library
- transformers
- Type
- gpt2
- Created
- Apr 12, 2024
- Updated
- Apr 14, 2024