Downloads · 30 days
8
16% of all-time downloads
Prompt-Guard-86M-tuned
gnurt2041/Prompt-Guard-86M-tuned
Prompt-Guard-86M-tuned is a text classification model from gnurt2041. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as llama3.1.
should probably proofread and complete it, then remove this comment. --
All-time downloads
49
Public
Parameters
279M
3.4 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors1.1 GB · 99%
At a glance
- Task
- Text Classification
- Library
- transformers
- License
- llama3.1
- Model type
- deberta-v2
- Access
- Public
- Created
- Oct 22, 2024
- Updated
- Oct 25, 2024
- SHA
- fde4f6fb
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. -->
results
This model is a fine-tuned version of meta-llama/Prompt-Guard-86M on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3940
- Accuracy: 0.8083
- Precision: 0.8493
- Recall: 0.8083
- F1: 0.8004
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: 3e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.4309 | 0.9895 | 59 | 0.3940 | 0.8083 | 0.8493 | 0.8083 | 0.8004 |
| 0.2471 | 1.9958 | 119 | 0.4489 | 0.8667 | 0.8809 | 0.8667 | 0.8646 |
| 0.308 | 2.9853 | 178 | 0.4891 | 0.875 | 0.8890 | 0.875 | 0.8745 |
| 0.0769 | 3.9916 | 238 | 0.5789 | 0.875 | 0.8763 | 0.875 | 0.8751 |
| 0.0185 | 4.9979 | 298 | 0.5860 | 0.9083 | 0.9091 | 0.9083 | 0.9082 |
| 0.1513 | 5.9874 | 357 | 0.7945 | 0.8417 | 0.8548 | 0.8417 | 0.8411 |
| 0.0262 | 6.9937 | 417 | 0.7072 | 0.8917 | 0.8917 | 0.8917 | 0.8916 |
| 0.0011 | 8.0 | 477 | 0.6887 | 0.9083 | 0.9108 | 0.9083 | 0.9080 |
| 0.0008 | 8.9895 | 536 | 0.7496 | 0.8917 | 0.8917 | 0.8917 | 0.8916 |
| 0.0007 | 9.8952 | 590 | 0.7500 | 0.9 | 0.9003 | 0.9 | 0.8999 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.19.1
- Task
- Text Classification
- Library
- transformers
- Type
- deberta-v2
- License
- llama3.1
- Created
- Oct 22, 2024
- Updated
- Oct 25, 2024