Hugging Face's logo

cgoosen
/
Prompt-Guard-finetuned-ctf-86M

Safetensors
deberta-v2
Generated from Trainer
Model card Files
xet
Community
cgoosen commited on
Commit
f59e963
·
verified ·
1 Parent(s): 4cb5985

cgoosen/prompt-tackler

Browse files
Files changed (3) hide show
  1. README.md +16 -10
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -5,6 +5,9 @@ tags:
5
  - generated_from_trainer
6
  metrics:
7
  - accuracy
 
 
 
8
  model-index:
9
  - name: Prompt-Guard-finetuned-ctf-86M
10
  results: []
@@ -17,8 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.0226
21
- - Accuracy: 0.9964
 
 
 
22
 
23
  ## Model description
24
 
@@ -47,14 +53,14 @@ The following hyperparameters were used during training:
47
 
48
  ### Training results
49
 
50
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|
52
- | 0.0291 | 1.0 | 2346 | 0.0315 | 0.9953 |
53
- | 0.0222 | 2.0 | 4692 | 0.0318 | 0.9953 |
54
- | 0.0081 | 3.0 | 7038 | 0.0226 | 0.9964 |
55
- | 0.0032 | 4.0 | 9384 | 0.0329 | 0.9966 |
56
- | 0.0031 | 5.0 | 11730 | 0.0352 | 0.9957 |
57
- | 0.0039 | 6.0 | 14076 | 0.0242 | 0.9974 |
58
 
59
 
60
  ### Framework versions
 
5
  - generated_from_trainer
6
  metrics:
7
  - accuracy
8
+ - precision
9
+ - recall
10
+ - f1
11
  model-index:
12
  - name: Prompt-Guard-finetuned-ctf-86M
13
  results: []
 
20
 
21
  This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.0093
24
+ - Accuracy: 0.9983
25
+ - Precision: 0.9983
26
+ - Recall: 0.9983
27
+ - F1: 0.9983
28
 
29
  ## Model description
30
 
 
53
 
54
  ### Training results
55
 
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
57
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
58
+ | 0.0225 | 1.0 | 4481 | 0.0095 | 0.9977 | 0.9977 | 0.9977 | 0.9977 |
59
+ | 0.0058 | 2.0 | 8962 | 0.0105 | 0.9980 | 0.9980 | 0.9980 | 0.9980 |
60
+ | 0.004 | 3.0 | 13443 | 0.0093 | 0.9983 | 0.9983 | 0.9983 | 0.9983 |
61
+ | 0.0036 | 4.0 | 17924 | 0.0130 | 0.9981 | 0.9981 | 0.9981 | 0.9981 |
62
+ | 0.0 | 5.0 | 22405 | 0.0138 | 0.9987 | 0.9987 | 0.9987 | 0.9987 |
63
+ | 0.0009 | 6.0 | 26886 | 0.0175 | 0.9981 | 0.9981 | 0.9981 | 0.9981 |
64
 
65
 
66
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:078563f4d4da764b13e136573021c0dfe14dbb3c168665d23a895b08e442c6cd
3
  size 737722356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:692024f3916b640470ffda774dabc14b20f421dbf7458d567f04a5b816a4e60b
3
  size 737722356
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38f9ca1e0d7904a29e057a2ece9bba73972fd0b1667a3bb847c67cde6d2061d2
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96678d179af42102cca8b1df9df88c6d46e58c7ebe55d0a669b285ae14e0a7a5
3
  size 5048