Hugging Face's logo

leomaurodesenv
/
bert-base-uncased-trustairlab-jailbreak-augmented

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
leomaurodesenv commited on
Commit
e64edea
·
verified ·
1 Parent(s): 68474bc

End of training

Browse files
Files changed (2) hide show
  1. README.md +14 -11
  2. model.safetensors +1 -1
README.md CHANGED
@@ -7,19 +7,19 @@ tags:
7
  metrics:
8
  - accuracy
9
  model-index:
10
- - name: bert-base-uncased-trustairlab-jailbreak
11
  results: []
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
  should probably proofread and complete it, then remove this comment. -->
16
 
17
- # bert-base-uncased-trustairlab-jailbreak
18
 
19
  This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.1904
22
- - Accuracy: 0.9388
23
 
24
  ## Model description
25
 
@@ -51,13 +51,16 @@ The following hyperparameters were used during training:
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
56
- | 0.2879 | 1.0 | 605 | 0.2115 | 0.9363 |
57
- | 0.1228 | 2.0 | 1210 | 0.1901 | 0.9396 |
58
- | 0.1572 | 3.0 | 1815 | 0.2256 | 0.9400 |
59
- | 0.1561 | 4.0 | 2420 | 0.2302 | 0.9396 |
60
- | 0.0600 | 5.0 | 3025 | 0.3227 | 0.9342 |
 
 
 
61
 
62
 
63
  ### Framework versions
 
7
  metrics:
8
  - accuracy
9
  model-index:
10
+ - name: bert-base-uncased-trustairlab-jailbreak-augmented
11
  results: []
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
  should probably proofread and complete it, then remove this comment. -->
16
 
17
+ # bert-base-uncased-trustairlab-jailbreak-augmented
18
 
19
  This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.1346
22
+ - Accuracy: 0.9598
23
 
24
  ## Model description
25
 
 
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
56
+ | 0.5493 | 1.0 | 4240 | 0.2043 | 0.9302 |
57
+ | 0.2353 | 2.0 | 8480 | 0.1689 | 0.9442 |
58
+ | 0.0884 | 3.0 | 12720 | 0.1558 | 0.9525 |
59
+ | 0.1884 | 4.0 | 16960 | 0.1752 | 0.9546 |
60
+ | 0.1707 | 5.0 | 21200 | 0.1340 | 0.9597 |
61
+ | 0.1012 | 6.0 | 25440 | 0.1505 | 0.9616 |
62
+ | 0.0637 | 7.0 | 29680 | 0.1591 | 0.9614 |
63
+ | 0.0655 | 8.0 | 33920 | 0.1762 | 0.9630 |
64
 
65
 
66
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e0154880ade76ff3067543c97e44e56a7126036e8d4e41db299c49613c07c8f
3
  size 437958624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:077adc5638bb503cd546163908aec75f8b2ba5135de2c8181a5ef2724ca5cce1
3
  size 437958624