Downloads · 30 days
34
1% of all-time downloads
protein-lm-gb1
mcneela/protein-lm-gb1
protein-lm-gb1 is a text classification model from mcneela. Use it when you need a label for a piece of text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
4.4K
Public
Repo size
3.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin924 MB · 100%
At a glance
- Task
- Text Classification
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Jan 9, 2023
- Updated
- Jan 9, 2023
- SHA
- 68ba0120
Try a prompt
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. -->
protein-lm-gb1
This model was trained from scratch on the gb1 dataset. It achieves the following results on the evaluation set:
- Loss: 4.9175
- Mse: 4.9175
- Rmse: 2.2175
- Mae: 1.9137
- R2: -0.0720
- Smape: 79.2041
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: 64
- eval_batch_size: 20
- 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 | Mse | Rmse | Mae | R2 | Smape |
|---|---|---|---|---|---|---|---|---|
| 5.202 | 1.0 | 7539 | 4.9090 | 4.9090 | 2.2156 | 1.9131 | -0.0702 | 79.1446 |
| 5.247 | 2.0 | 15078 | 4.9849 | 4.9849 | 2.2327 | 1.9185 | -0.0867 | 79.6722 |
| 5.2129 | 3.0 | 22617 | 4.9175 | 4.9175 | 2.2175 | 1.9137 | -0.0720 | 79.2041 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
- Task
- Text Classification
- Library
- transformers
- Type
- bert
- Created
- Jan 9, 2023
- Updated
- Jan 9, 2023