Hugging Face's logo

hurtmongoose
/
bert-base-detect-jailbreak

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
hurtmongoose commited on
Commit
986c343
·
verified ·
1 Parent(s): 5e0f2e6

End of training

Browse files
Files changed (2) hide show
  1. README.md +24 -24
  2. model.safetensors +1 -1
README.md CHANGED
@@ -21,13 +21,13 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.1676
25
- - Accuracy: 0.9463
26
- - Precision: 0.7756
27
- - Recall: 0.7089
28
- - F1: 0.7407
29
- - Balanced Accuracy: 0.8420
30
- - Mcc: 0.7118
31
 
32
  ## Model description
33
 
@@ -47,10 +47,10 @@ More information needed
47
 
48
  The following hyperparameters were used during training:
49
  - learning_rate: 2e-05
50
- - train_batch_size: 16
51
- - eval_batch_size: 32
52
  - seed: 42
53
- - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
54
  - lr_scheduler_type: linear
55
  - num_epochs: 10
56
 
@@ -58,21 +58,21 @@ The following hyperparameters were used during training:
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Balanced Accuracy | Mcc |
60
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-----------------:|:------:|
61
- | 0.16 | 1.0 | 685 | 0.1588 | 0.9504 | 0.7967 | 0.7305 | 0.7622 | 0.8539 | 0.7354 |
62
- | 0.1094 | 2.0 | 1370 | 0.1731 | 0.9477 | 0.7711 | 0.7380 | 0.7542 | 0.8557 | 0.7252 |
63
- | 0.1255 | 3.0 | 2055 | 0.1881 | 0.9502 | 0.8045 | 0.7154 | 0.7573 | 0.8471 | 0.7312 |
64
- | 0.0686 | 4.0 | 2740 | 0.2148 | 0.9507 | 0.8056 | 0.7204 | 0.7606 | 0.8496 | 0.7347 |
65
- | 0.048 | 5.0 | 3425 | 0.2793 | 0.9493 | 0.8136 | 0.6927 | 0.7483 | 0.8367 | 0.7232 |
66
- | 0.0276 | 6.0 | 4110 | 0.3122 | 0.9477 | 0.7960 | 0.6977 | 0.7436 | 0.8380 | 0.7166 |
67
- | 0.0194 | 7.0 | 4795 | 0.3583 | 0.9480 | 0.8224 | 0.6650 | 0.7354 | 0.8237 | 0.7118 |
68
- | 0.0173 | 8.0 | 5480 | 0.3802 | 0.9461 | 0.7809 | 0.7003 | 0.7384 | 0.8381 | 0.7097 |
69
- | 0.0121 | 9.0 | 6165 | 0.3939 | 0.9463 | 0.7880 | 0.6927 | 0.7373 | 0.8350 | 0.7093 |
70
- | 0.0052 | 10.0 | 6850 | 0.3984 | 0.9472 | 0.7914 | 0.6977 | 0.7416 | 0.8377 | 0.7141 |
71
 
72
 
73
  ### Framework versions
74
 
75
- - Transformers 4.57.2
76
- - Pytorch 2.9.0+cu126
77
- - Datasets 4.0.0
78
- - Tokenizers 0.22.1
 
21
 
22
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.3486
25
+ - Accuracy: 0.8931
26
+ - Precision: 0.9206
27
+ - Recall: 0.8657
28
+ - F1: 0.8923
29
+ - Balanced Accuracy: 0.8938
30
+ - Mcc: 0.7879
31
 
32
  ## Model description
33
 
 
47
 
48
  The following hyperparameters were used during training:
49
  - learning_rate: 2e-05
50
+ - train_batch_size: 32
51
+ - eval_batch_size: 64
52
  - seed: 42
53
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
54
  - lr_scheduler_type: linear
55
  - num_epochs: 10
56
 
 
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Balanced Accuracy | Mcc |
60
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-----------------:|:------:|
61
+ | No log | 1.0 | 99 | 0.2730 | 0.9059 | 0.9305 | 0.8788 | 0.9039 | 0.9061 | 0.8130 |
62
+ | 0.4532 | 2.0 | 198 | 0.2610 | 0.9059 | 0.9548 | 0.8535 | 0.9013 | 0.9063 | 0.8165 |
63
+ | 0.2683 | 3.0 | 297 | 0.2622 | 0.9008 | 0.9441 | 0.8535 | 0.8966 | 0.9011 | 0.8054 |
64
+ | 0.202 | 4.0 | 396 | 0.2914 | 0.9109 | 0.9179 | 0.9040 | 0.9109 | 0.9110 | 0.8220 |
65
+ | 0.1308 | 5.0 | 495 | 0.3012 | 0.9135 | 0.9362 | 0.8889 | 0.9119 | 0.9137 | 0.8281 |
66
+ | 0.0856 | 6.0 | 594 | 0.3709 | 0.8906 | 0.8818 | 0.9040 | 0.8928 | 0.8905 | 0.7814 |
67
+ | 0.0622 | 7.0 | 693 | 0.4141 | 0.8957 | 0.8905 | 0.9040 | 0.8972 | 0.8956 | 0.7914 |
68
+ | 0.0366 | 8.0 | 792 | 0.4711 | 0.8957 | 0.8720 | 0.9293 | 0.8998 | 0.8954 | 0.7930 |
69
+ | 0.0262 | 9.0 | 891 | 0.4318 | 0.8982 | 0.8990 | 0.8990 | 0.8990 | 0.8982 | 0.7964 |
70
+ | 0.0145 | 10.0 | 990 | 0.4440 | 0.8957 | 0.8867 | 0.9091 | 0.8978 | 0.8956 | 0.7916 |
71
 
72
 
73
  ### Framework versions
74
 
75
+ - Transformers 4.53.3
76
+ - Pytorch 2.6.0+cu124
77
+ - Datasets 4.3.0
78
+ - Tokenizers 0.21.4
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbfef5d949dcdb1004db361000a652a90e62cf97f4df51b8d99fa16d9b59fe4c
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51de9d65c5ca34331de309f901b6a88363a87c5cceeb8c9f7de0feee989fc1ef
3
  size 437958648