Hugging Face's logo

POBonin
/
setfit-quebec-profanity-classifier

Text Classification
setfit
Safetensors
sentence-transformers
xlm-roberta
generated_from_setfit_trainer
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
Community
POBonin commited on
Commit
052e1bf
·
verified ·
1 Parent(s): 528ecc3

Add SetFit model

Browse files
Files changed (6) hide show
  1. README.md +15 -25
  2. config.json +1 -2
  3. config_sentence_transformers.json +2 -2
  4. model.safetensors +1 -1
  5. model_head.pkl +1 -1
  6. tokenizer_config.json +1 -0
README.md CHANGED
@@ -153,36 +153,26 @@ preds = model("esti")
153
  - load_best_model_at_end: True
154
 
155
  ### Training Results
156
- | Epoch | Step | Training Loss | Validation Loss |
157
- |:-------:|:----:|:-------------:|:---------------:|
158
- | 0.0175 | 1 | 0.2373 | - |
159
- | 0.8772 | 50 | 0.2157 | 0.0794 |
160
- | 1.7544 | 100 | 0.0818 | 0.0061 |
161
- | 2.6316 | 150 | 0.0014 | 0.0069 |
162
- | 3.5088 | 200 | 0.0004 | 0.0086 |
163
- | 4.3860 | 250 | 0.0003 | 0.0057 |
164
- | 5.2632 | 300 | 0.0003 | 0.0103 |
165
- | 6.1404 | 350 | 0.0002 | 0.0092 |
166
- | 7.0175 | 400 | 0.0002 | 0.0169 |
167
- | 7.8947 | 450 | 0.0002 | 0.0110 |
168
- | 8.7719 | 500 | 0.0002 | 0.0135 |
169
- | 9.6491 | 550 | 0.0002 | 0.0131 |
170
- | 10.5263 | 600 | 0.0001 | 0.0120 |
171
- | 11.4035 | 650 | 0.0001 | 0.0114 |
172
- | 12.2807 | 700 | 0.0001 | 0.0128 |
173
- | 13.1579 | 750 | 0.0001 | 0.0135 |
174
- | 14.0351 | 800 | 0.0001 | 0.0142 |
175
- | 14.9123 | 850 | 0.0001 | 0.0156 |
176
- | 15.7895 | 900 | 0.0001 | 0.0160 |
177
 
178
  ### Framework Versions
179
  - Python: 3.12.10
180
  - SetFit: 1.1.2
181
  - Sentence Transformers: 4.1.0
182
- - Transformers: 4.45.1
183
- - PyTorch: 2.7.0+cu128
184
- - Datasets: 3.0.1
185
- - Tokenizers: 0.20.1
186
 
187
  ## Citation
188
 
 
153
  - load_best_model_at_end: True
154
 
155
  ### Training Results
156
+ | Epoch | Step | Training Loss | Validation Loss |
157
+ |:------:|:----:|:-------------:|:---------------:|
158
+ | 0.0175 | 1 | 0.2373 | - |
159
+ | 0.8772 | 50 | 0.2157 | 0.0794 |
160
+ | 1.7544 | 100 | 0.0818 | 0.0061 |
161
+ | 2.6316 | 150 | 0.0014 | 0.0069 |
162
+ | 3.5088 | 200 | 0.0004 | 0.0086 |
163
+ | 4.3860 | 250 | 0.0003 | 0.0057 |
164
+ | 5.2632 | 300 | 0.0003 | 0.0103 |
165
+ | 6.1404 | 350 | 0.0002 | 0.0092 |
166
+ | 7.0175 | 400 | 0.0002 | 0.0169 |
 
 
 
 
 
 
 
 
 
 
167
 
168
  ### Framework Versions
169
  - Python: 3.12.10
170
  - SetFit: 1.1.2
171
  - Sentence Transformers: 4.1.0
172
+ - Transformers: 4.51.3
173
+ - PyTorch: 2.6.0+cu126
174
+ - Datasets: 2.19.1
175
+ - Tokenizers: 0.21.1
176
 
177
  ## Citation
178
 
config.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "_name_or_path": "sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
3
  "architectures": [
4
  "XLMRobertaModel"
5
  ],
@@ -22,7 +21,7 @@
22
  "pad_token_id": 1,
23
  "position_embedding_type": "absolute",
24
  "torch_dtype": "float32",
25
- "transformers_version": "4.45.1",
26
  "type_vocab_size": 1,
27
  "use_cache": true,
28
  "vocab_size": 250002
 
1
  {
 
2
  "architectures": [
3
  "XLMRobertaModel"
4
  ],
 
21
  "pad_token_id": 1,
22
  "position_embedding_type": "absolute",
23
  "torch_dtype": "float32",
24
+ "transformers_version": "4.51.3",
25
  "type_vocab_size": 1,
26
  "use_cache": true,
27
  "vocab_size": 250002
config_sentence_transformers.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "__version__": {
3
  "sentence_transformers": "4.1.0",
4
- "transformers": "4.45.1",
5
- "pytorch": "2.7.0+cu128"
6
  },
7
  "prompts": {},
8
  "default_prompt_name": null,
 
1
  {
2
  "__version__": {
3
  "sentence_transformers": "4.1.0",
4
+ "transformers": "4.51.3",
5
+ "pytorch": "2.6.0+cu126"
6
  },
7
  "prompts": {},
8
  "default_prompt_name": null,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f560cb215e7638a135db656da192436020d775932bcf4465f06c8672a6f70330
3
  size 1112197096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c44b5973c58acf265e54b09cd085f68a513c1a7547e09a8b7e275cbb7001ecf
3
  size 1112197096
model_head.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f9956302a9fa640e71c5c62330e6f942505d6db8038fefb9f145a70bea62964
3
  size 32159
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8f6a53138111ff4e76f97a2b8b08d7ccf9dccc396c47f30e0448a4c03db3abc
3
  size 32159
tokenizer_config.json CHANGED
@@ -45,6 +45,7 @@
45
  "clean_up_tokenization_spaces": false,
46
  "cls_token": "<s>",
47
  "eos_token": "</s>",
 
48
  "mask_token": "<mask>",
49
  "max_length": 128,
50
  "model_max_length": 128,
 
45
  "clean_up_tokenization_spaces": false,
46
  "cls_token": "<s>",
47
  "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
  "mask_token": "<mask>",
50
  "max_length": 128,
51
  "model_max_length": 128,