Hugging Face's logo

dcarpintero
/
pangolin-guard-base

Text Classification
Transformers
Safetensors
modernbert
ai-safety
safeguards
guardrails
Model card Files Community
dcarpintero commited on
Commit
4f5393f
·
verified ·
1 Parent(s): e6042ce

End of training

Browse files
Files changed (4) hide show
  1. README.md +25 -25
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.0216
23
- - F1: 0.9909
24
- - Accuracy: 0.9940
25
 
26
  ## Model description
27
 
@@ -52,30 +52,30 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
54
  |:-------------:|:------:|:----:|:---------------:|:------:|:--------:|
55
- | 0.1786 | 0.1042 | 100 | 0.0687 | 0.9646 | 0.9765 |
56
- | 0.0807 | 0.2083 | 200 | 0.0540 | 0.9709 | 0.9808 |
57
- | 0.0479 | 0.3125 | 300 | 0.0486 | 0.9733 | 0.9824 |
58
- | 0.043 | 0.4167 | 400 | 0.0495 | 0.9751 | 0.9833 |
59
- | 0.0414 | 0.5208 | 500 | 0.0364 | 0.9824 | 0.9884 |
60
- | 0.0369 | 0.625 | 600 | 0.0396 | 0.9791 | 0.9861 |
61
- | 0.0341 | 0.7292 | 700 | 0.0292 | 0.9854 | 0.9904 |
62
- | 0.0334 | 0.8333 | 800 | 0.0276 | 0.9860 | 0.9908 |
63
- | 0.0278 | 0.9375 | 900 | 0.0272 | 0.9872 | 0.9916 |
64
- | 0.0203 | 1.0417 | 1000 | 0.0277 | 0.9884 | 0.9924 |
65
- | 0.012 | 1.1458 | 1100 | 0.0280 | 0.9897 | 0.9932 |
66
- | 0.0118 | 1.25 | 1200 | 0.0268 | 0.9889 | 0.9926 |
67
- | 0.0075 | 1.3542 | 1300 | 0.0270 | 0.9904 | 0.9937 |
68
- | 0.0112 | 1.4583 | 1400 | 0.0300 | 0.9877 | 0.9918 |
69
- | 0.0126 | 1.5625 | 1500 | 0.0233 | 0.9886 | 0.9924 |
70
- | 0.0108 | 1.6667 | 1600 | 0.0214 | 0.9910 | 0.9941 |
71
- | 0.0101 | 1.7708 | 1700 | 0.0222 | 0.9911 | 0.9941 |
72
- | 0.0058 | 1.875 | 1800 | 0.0230 | 0.9911 | 0.9941 |
73
- | 0.0095 | 1.9792 | 1900 | 0.0216 | 0.9909 | 0.9940 |
74
 
75
 
76
  ### Framework versions
77
 
78
- - Transformers 4.48.3
79
  - Pytorch 2.6.0+cu124
80
- - Datasets 3.4.0
81
- - Tokenizers 0.21.0
 
19
 
20
  This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.0194
23
+ - F1: 0.9906
24
+ - Accuracy: 0.9941
25
 
26
  ## Model description
27
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy |
54
  |:-------------:|:------:|:----:|:---------------:|:------:|:--------:|
55
+ | 0.1811 | 0.1042 | 100 | 0.0917 | 0.9524 | 0.9690 |
56
+ | 0.0781 | 0.2083 | 200 | 0.0568 | 0.9682 | 0.9802 |
57
+ | 0.0488 | 0.3125 | 300 | 0.0415 | 0.9786 | 0.9866 |
58
+ | 0.052 | 0.4167 | 400 | 0.0404 | 0.9801 | 0.9876 |
59
+ | 0.0506 | 0.5208 | 500 | 0.0331 | 0.9831 | 0.9892 |
60
+ | 0.0352 | 0.625 | 600 | 0.0355 | 0.9833 | 0.9894 |
61
+ | 0.0374 | 0.7292 | 700 | 0.0263 | 0.9867 | 0.9916 |
62
+ | 0.0281 | 0.8333 | 800 | 0.0284 | 0.9877 | 0.9922 |
63
+ | 0.0241 | 0.9375 | 900 | 0.0428 | 0.9834 | 0.9894 |
64
+ | 0.025 | 1.0417 | 1000 | 0.0266 | 0.9883 | 0.9926 |
65
+ | 0.0096 | 1.1458 | 1100 | 0.0300 | 0.9873 | 0.9920 |
66
+ | 0.0125 | 1.25 | 1200 | 0.0237 | 0.9892 | 0.9932 |
67
+ | 0.0075 | 1.3542 | 1300 | 0.0251 | 0.9894 | 0.9933 |
68
+ | 0.0118 | 1.4583 | 1400 | 0.0249 | 0.9883 | 0.9926 |
69
+ | 0.014 | 1.5625 | 1500 | 0.0199 | 0.9901 | 0.9937 |
70
+ | 0.0067 | 1.6667 | 1600 | 0.0215 | 0.9902 | 0.9938 |
71
+ | 0.0088 | 1.7708 | 1700 | 0.0201 | 0.9909 | 0.9943 |
72
+ | 0.0079 | 1.875 | 1800 | 0.0199 | 0.9906 | 0.9941 |
73
+ | 0.0118 | 1.9792 | 1900 | 0.0194 | 0.9906 | 0.9941 |
74
 
75
 
76
  ### Framework versions
77
 
78
+ - Transformers 4.49.0
79
  - Pytorch 2.6.0+cu124
80
+ - Datasets 3.4.1
81
+ - Tokenizers 0.21.1
config.json CHANGED
@@ -51,6 +51,6 @@
51
  "sparse_pred_ignore_index": -100,
52
  "sparse_prediction": false,
53
  "torch_dtype": "float32",
54
- "transformers_version": "4.48.3",
55
  "vocab_size": 50368
56
  }
 
51
  "sparse_pred_ignore_index": -100,
52
  "sparse_prediction": false,
53
  "torch_dtype": "float32",
54
+ "transformers_version": "4.49.0",
55
  "vocab_size": 50368
56
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6018f40a93f72a2f93c73dbb987e6ed9995eae52f4b6d76d7d5885a293e545cb
3
  size 598439784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fedb5d7a51f4028814702ffad34e06d624b39acffb6f68f2ba24f597ab36b34
3
  size 598439784
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1b815b19eec8d4d382b6ffaf2f2a5366fc1f24b46d943961bbafdf336f5fddb
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16ab2834506964c4d5c29cb8277af70fd76a644d509a8e3ccb1e03cfc74e0bf9
3
  size 5368