Commit
•
ddededf
1
Parent(s):
9697027
Push model using huggingface_hub.
Browse files- .gitattributes +1 -0
- 1_Pooling/config.json +1 -1
- README.md +24 -245
- config.json +15 -18
- model.safetensors +2 -2
- model_head.pkl +2 -2
- sentence_bert_config.json +2 -2
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +20 -6
- tokenizer.json +0 -0
- tokenizer_config.json +20 -22
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
1_Pooling/config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"word_embedding_dimension":
|
| 3 |
"pooling_mode_cls_token": true,
|
| 4 |
"pooling_mode_mean_tokens": false,
|
| 5 |
"pooling_mode_max_tokens": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"word_embedding_dimension": 1024,
|
| 3 |
"pooling_mode_cls_token": true,
|
| 4 |
"pooling_mode_mean_tokens": false,
|
| 5 |
"pooling_mode_max_tokens": false,
|
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
base_model: BAAI/bge-
|
| 3 |
library_name: setfit
|
| 4 |
metrics:
|
| 5 |
- accuracy
|
|
@@ -18,7 +18,7 @@ widget:
|
|
| 18 |
- text: Konstrukcja łóżka piętrowego jest wadliwa, elementy nie pasują do siebie.
|
| 19 |
inference: true
|
| 20 |
model-index:
|
| 21 |
-
- name: SetFit with BAAI/bge-
|
| 22 |
results:
|
| 23 |
- task:
|
| 24 |
type: text-classification
|
|
@@ -29,13 +29,13 @@ model-index:
|
|
| 29 |
split: test
|
| 30 |
metrics:
|
| 31 |
- type: accuracy
|
| 32 |
-
value: 0.
|
| 33 |
name: Accuracy
|
| 34 |
---
|
| 35 |
|
| 36 |
-
# SetFit with BAAI/bge-
|
| 37 |
|
| 38 |
-
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [BAAI/bge-
|
| 39 |
|
| 40 |
The model has been trained using an efficient few-shot learning technique that involves:
|
| 41 |
|
|
@@ -46,9 +46,9 @@ The model has been trained using an efficient few-shot learning technique that i
|
|
| 46 |
|
| 47 |
### Model Description
|
| 48 |
- **Model Type:** SetFit
|
| 49 |
-
- **Sentence Transformer body:** [BAAI/bge-
|
| 50 |
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
| 51 |
-
- **Maximum Sequence Length:**
|
| 52 |
- **Number of Classes:** 4 classes
|
| 53 |
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
| 54 |
<!-- - **Language:** Unknown -->
|
|
@@ -61,19 +61,19 @@ The model has been trained using an efficient few-shot learning technique that i
|
|
| 61 |
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
| 62 |
|
| 63 |
### Model Labels
|
| 64 |
-
| Label | Examples
|
| 65 |
-
|
| 66 |
-
|
|
| 67 |
-
|
|
| 68 |
-
|
|
| 69 |
-
|
|
| 70 |
|
| 71 |
## Evaluation
|
| 72 |
|
| 73 |
### Metrics
|
| 74 |
| Label | Accuracy |
|
| 75 |
|:--------|:---------|
|
| 76 |
-
| **all** | 0.
|
| 77 |
|
| 78 |
## Uses
|
| 79 |
|
|
@@ -123,16 +123,16 @@ preds = model("Półki regału Biblioteka są zbyt wąskie.")
|
|
| 123 |
## Training Details
|
| 124 |
|
| 125 |
### Training Set Metrics
|
| 126 |
-
| Training set | Min | Median
|
| 127 |
-
|
| 128 |
-
| Word count | 4 | 10.
|
| 129 |
|
| 130 |
| Label | Training Sample Count |
|
| 131 |
|:---------------------------------|:----------------------|
|
| 132 |
-
| uszkodzenia |
|
| 133 |
-
| wady fabryczne |
|
| 134 |
-
| niezgodność towaru z zamówieniem |
|
| 135 |
-
| błędny montaż |
|
| 136 |
|
| 137 |
### Training Hyperparameters
|
| 138 |
- batch_size: (32, 32)
|
|
@@ -155,230 +155,9 @@ preds = model("Półki regału Biblioteka są zbyt wąskie.")
|
|
| 155 |
### Training Results
|
| 156 |
| Epoch | Step | Training Loss | Validation Loss |
|
| 157 |
|:------:|:----:|:-------------:|:---------------:|
|
| 158 |
-
| 0.
|
| 159 |
-
|
|
| 160 |
-
|
|
| 161 |
-
| 0.3125 | 30 | 0.2249 | - |
|
| 162 |
-
| 0.4167 | 40 | 0.2265 | - |
|
| 163 |
-
| 0.5208 | 50 | 0.2153 | - |
|
| 164 |
-
| 0.625 | 60 | 0.2043 | - |
|
| 165 |
-
| 0.7292 | 70 | 0.2033 | - |
|
| 166 |
-
| 0.8333 | 80 | 0.204 | - |
|
| 167 |
-
| 0.9375 | 90 | 0.1648 | - |
|
| 168 |
-
| 1.0417 | 100 | 0.1452 | - |
|
| 169 |
-
| 1.1458 | 110 | 0.1219 | - |
|
| 170 |
-
| 1.25 | 120 | 0.1062 | - |
|
| 171 |
-
| 1.3542 | 130 | 0.0921 | - |
|
| 172 |
-
| 1.4583 | 140 | 0.0803 | - |
|
| 173 |
-
| 1.5625 | 150 | 0.0559 | - |
|
| 174 |
-
| 1.6667 | 160 | 0.0339 | - |
|
| 175 |
-
| 1.7708 | 170 | 0.0258 | - |
|
| 176 |
-
| 1.875 | 180 | 0.0153 | - |
|
| 177 |
-
| 1.9792 | 190 | 0.0095 | - |
|
| 178 |
-
| 2.0833 | 200 | 0.0074 | - |
|
| 179 |
-
| 2.1875 | 210 | 0.0076 | - |
|
| 180 |
-
| 2.2917 | 220 | 0.0058 | - |
|
| 181 |
-
| 2.3958 | 230 | 0.005 | - |
|
| 182 |
-
| 2.5 | 240 | 0.0047 | - |
|
| 183 |
-
| 2.6042 | 250 | 0.0043 | - |
|
| 184 |
-
| 2.7083 | 260 | 0.0041 | - |
|
| 185 |
-
| 2.8125 | 270 | 0.0038 | - |
|
| 186 |
-
| 2.9167 | 280 | 0.0035 | - |
|
| 187 |
-
| 3.0208 | 290 | 0.0034 | - |
|
| 188 |
-
| 3.125 | 300 | 0.0033 | - |
|
| 189 |
-
| 3.2292 | 310 | 0.0035 | - |
|
| 190 |
-
| 3.3333 | 320 | 0.0028 | - |
|
| 191 |
-
| 3.4375 | 330 | 0.0031 | - |
|
| 192 |
-
| 3.5417 | 340 | 0.0028 | - |
|
| 193 |
-
| 3.6458 | 350 | 0.0027 | - |
|
| 194 |
-
| 3.75 | 360 | 0.0025 | - |
|
| 195 |
-
| 3.8542 | 370 | 0.0025 | - |
|
| 196 |
-
| 3.9583 | 380 | 0.0024 | - |
|
| 197 |
-
| 4.0625 | 390 | 0.0023 | - |
|
| 198 |
-
| 4.1667 | 400 | 0.0023 | - |
|
| 199 |
-
| 4.2708 | 410 | 0.0022 | - |
|
| 200 |
-
| 4.375 | 420 | 0.0021 | - |
|
| 201 |
-
| 4.4792 | 430 | 0.0022 | - |
|
| 202 |
-
| 4.5833 | 440 | 0.002 | - |
|
| 203 |
-
| 4.6875 | 450 | 0.0022 | - |
|
| 204 |
-
| 4.7917 | 460 | 0.0019 | - |
|
| 205 |
-
| 4.8958 | 470 | 0.0021 | - |
|
| 206 |
-
| 5.0 | 480 | 0.0018 | - |
|
| 207 |
-
| 5.1042 | 490 | 0.002 | - |
|
| 208 |
-
| 5.2083 | 500 | 0.002 | - |
|
| 209 |
-
| 5.3125 | 510 | 0.0017 | - |
|
| 210 |
-
| 5.4167 | 520 | 0.002 | - |
|
| 211 |
-
| 5.5208 | 530 | 0.0017 | - |
|
| 212 |
-
| 5.625 | 540 | 0.0018 | - |
|
| 213 |
-
| 5.7292 | 550 | 0.0016 | - |
|
| 214 |
-
| 5.8333 | 560 | 0.0016 | - |
|
| 215 |
-
| 5.9375 | 570 | 0.0015 | - |
|
| 216 |
-
| 6.0417 | 580 | 0.0014 | - |
|
| 217 |
-
| 6.1458 | 590 | 0.0017 | - |
|
| 218 |
-
| 6.25 | 600 | 0.0016 | - |
|
| 219 |
-
| 6.3542 | 610 | 0.0017 | - |
|
| 220 |
-
| 6.4583 | 620 | 0.0016 | - |
|
| 221 |
-
| 6.5625 | 630 | 0.0017 | - |
|
| 222 |
-
| 6.6667 | 640 | 0.0014 | - |
|
| 223 |
-
| 6.7708 | 650 | 0.0014 | - |
|
| 224 |
-
| 6.875 | 660 | 0.0016 | - |
|
| 225 |
-
| 6.9792 | 670 | 0.0015 | - |
|
| 226 |
-
| 7.0833 | 680 | 0.0015 | - |
|
| 227 |
-
| 7.1875 | 690 | 0.0014 | - |
|
| 228 |
-
| 7.2917 | 700 | 0.0015 | - |
|
| 229 |
-
| 7.3958 | 710 | 0.0014 | - |
|
| 230 |
-
| 7.5 | 720 | 0.0015 | - |
|
| 231 |
-
| 7.6042 | 730 | 0.0014 | - |
|
| 232 |
-
| 7.7083 | 740 | 0.0014 | - |
|
| 233 |
-
| 7.8125 | 750 | 0.0014 | - |
|
| 234 |
-
| 7.9167 | 760 | 0.0015 | - |
|
| 235 |
-
| 8.0208 | 770 | 0.0013 | - |
|
| 236 |
-
| 8.125 | 780 | 0.0014 | - |
|
| 237 |
-
| 8.2292 | 790 | 0.0014 | - |
|
| 238 |
-
| 8.3333 | 800 | 0.0014 | - |
|
| 239 |
-
| 8.4375 | 810 | 0.0014 | - |
|
| 240 |
-
| 8.5417 | 820 | 0.0014 | - |
|
| 241 |
-
| 8.6458 | 830 | 0.0014 | - |
|
| 242 |
-
| 8.75 | 840 | 0.0013 | - |
|
| 243 |
-
| 8.8542 | 850 | 0.0013 | - |
|
| 244 |
-
| 8.9583 | 860 | 0.0013 | - |
|
| 245 |
-
| 9.0625 | 870 | 0.0013 | - |
|
| 246 |
-
| 9.1667 | 880 | 0.0014 | - |
|
| 247 |
-
| 9.2708 | 890 | 0.0013 | - |
|
| 248 |
-
| 9.375 | 900 | 0.0012 | - |
|
| 249 |
-
| 9.4792 | 910 | 0.0013 | - |
|
| 250 |
-
| 9.5833 | 920 | 0.0012 | - |
|
| 251 |
-
| 9.6875 | 930 | 0.0013 | - |
|
| 252 |
-
| 9.7917 | 940 | 0.0013 | - |
|
| 253 |
-
| 9.8958 | 950 | 0.0013 | - |
|
| 254 |
-
| 10.0 | 960 | 0.0014 | - |
|
| 255 |
-
| 0.0008 | 1 | 0.2276 | - |
|
| 256 |
-
| 0.0083 | 10 | 0.2361 | - |
|
| 257 |
-
| 0.0167 | 20 | 0.1815 | - |
|
| 258 |
-
| 0.0250 | 30 | 0.2036 | - |
|
| 259 |
-
| 0.0333 | 40 | 0.1783 | - |
|
| 260 |
-
| 0.0416 | 50 | 0.1486 | - |
|
| 261 |
-
| 0.0500 | 60 | 0.191 | - |
|
| 262 |
-
| 0.0583 | 70 | 0.1741 | - |
|
| 263 |
-
| 0.0104 | 1 | 0.0021 | - |
|
| 264 |
-
| 0.1042 | 10 | 0.002 | - |
|
| 265 |
-
| 0.2083 | 20 | 0.0015 | - |
|
| 266 |
-
| 0.3125 | 30 | 0.0015 | - |
|
| 267 |
-
| 0.4167 | 40 | 0.0013 | - |
|
| 268 |
-
| 0.5208 | 50 | 0.0013 | - |
|
| 269 |
-
| 0.625 | 60 | 0.0012 | - |
|
| 270 |
-
| 0.7292 | 70 | 0.0011 | - |
|
| 271 |
-
| 0.8333 | 80 | 0.0012 | - |
|
| 272 |
-
| 0.9375 | 90 | 0.0011 | - |
|
| 273 |
-
| 1.0417 | 100 | 0.001 | - |
|
| 274 |
-
| 1.1458 | 110 | 0.001 | - |
|
| 275 |
-
| 1.25 | 120 | 0.0009 | - |
|
| 276 |
-
| 1.3542 | 130 | 0.0009 | - |
|
| 277 |
-
| 1.4583 | 140 | 0.0008 | - |
|
| 278 |
-
| 1.5625 | 150 | 0.0009 | - |
|
| 279 |
-
| 1.6667 | 160 | 0.0009 | - |
|
| 280 |
-
| 1.7708 | 170 | 0.0008 | - |
|
| 281 |
-
| 1.875 | 180 | 0.0008 | - |
|
| 282 |
-
| 1.9792 | 190 | 0.0007 | - |
|
| 283 |
-
| 2.0833 | 200 | 0.0007 | - |
|
| 284 |
-
| 2.1875 | 210 | 0.0007 | - |
|
| 285 |
-
| 2.2917 | 220 | 0.0007 | - |
|
| 286 |
-
| 2.3958 | 230 | 0.0006 | - |
|
| 287 |
-
| 2.5 | 240 | 0.0007 | - |
|
| 288 |
-
| 2.6042 | 250 | 0.0007 | - |
|
| 289 |
-
| 2.7083 | 260 | 0.0007 | - |
|
| 290 |
-
| 2.8125 | 270 | 0.0006 | - |
|
| 291 |
-
| 2.9167 | 280 | 0.0006 | - |
|
| 292 |
-
| 3.0208 | 290 | 0.0006 | - |
|
| 293 |
-
| 3.125 | 300 | 0.0006 | - |
|
| 294 |
-
| 3.2292 | 310 | 0.0006 | - |
|
| 295 |
-
| 3.3333 | 320 | 0.0006 | - |
|
| 296 |
-
| 3.4375 | 330 | 0.0006 | - |
|
| 297 |
-
| 3.5417 | 340 | 0.0006 | - |
|
| 298 |
-
| 3.6458 | 350 | 0.0005 | - |
|
| 299 |
-
| 3.75 | 360 | 0.0005 | - |
|
| 300 |
-
| 3.8542 | 370 | 0.0006 | - |
|
| 301 |
-
| 3.9583 | 380 | 0.0005 | - |
|
| 302 |
-
| 4.0625 | 390 | 0.0005 | - |
|
| 303 |
-
| 4.1667 | 400 | 0.0005 | - |
|
| 304 |
-
| 4.2708 | 410 | 0.0005 | - |
|
| 305 |
-
| 4.375 | 420 | 0.0006 | - |
|
| 306 |
-
| 4.4792 | 430 | 0.0005 | - |
|
| 307 |
-
| 4.5833 | 440 | 0.0005 | - |
|
| 308 |
-
| 4.6875 | 450 | 0.0005 | - |
|
| 309 |
-
| 4.7917 | 460 | 0.0005 | - |
|
| 310 |
-
| 4.8958 | 470 | 0.0005 | - |
|
| 311 |
-
| 5.0 | 480 | 0.0004 | - |
|
| 312 |
-
| 5.1042 | 490 | 0.0005 | - |
|
| 313 |
-
| 5.2083 | 500 | 0.0005 | - |
|
| 314 |
-
| 5.3125 | 510 | 0.0004 | - |
|
| 315 |
-
| 5.4167 | 520 | 0.0005 | - |
|
| 316 |
-
| 5.5208 | 530 | 0.0005 | - |
|
| 317 |
-
| 5.625 | 540 | 0.0005 | - |
|
| 318 |
-
| 5.7292 | 550 | 0.0005 | - |
|
| 319 |
-
| 5.8333 | 560 | 0.0004 | - |
|
| 320 |
-
| 5.9375 | 570 | 0.0004 | - |
|
| 321 |
-
| 6.0417 | 580 | 0.0004 | - |
|
| 322 |
-
| 6.1458 | 590 | 0.0004 | - |
|
| 323 |
-
| 6.25 | 600 | 0.0004 | - |
|
| 324 |
-
| 6.3542 | 610 | 0.0005 | - |
|
| 325 |
-
| 6.4583 | 620 | 0.0004 | - |
|
| 326 |
-
| 6.5625 | 630 | 0.0005 | - |
|
| 327 |
-
| 6.6667 | 640 | 0.0004 | - |
|
| 328 |
-
| 6.7708 | 650 | 0.0004 | - |
|
| 329 |
-
| 6.875 | 660 | 0.0004 | - |
|
| 330 |
-
| 6.9792 | 670 | 0.0004 | - |
|
| 331 |
-
| 7.0833 | 680 | 0.0004 | - |
|
| 332 |
-
| 7.1875 | 690 | 0.0004 | - |
|
| 333 |
-
| 7.2917 | 700 | 0.0004 | - |
|
| 334 |
-
| 7.3958 | 710 | 0.0004 | - |
|
| 335 |
-
| 7.5 | 720 | 0.0004 | - |
|
| 336 |
-
| 7.6042 | 730 | 0.0004 | - |
|
| 337 |
-
| 7.7083 | 740 | 0.0004 | - |
|
| 338 |
-
| 7.8125 | 750 | 0.0004 | - |
|
| 339 |
-
| 7.9167 | 760 | 0.0004 | - |
|
| 340 |
-
| 8.0208 | 770 | 0.0004 | - |
|
| 341 |
-
| 8.125 | 780 | 0.0004 | - |
|
| 342 |
-
| 8.2292 | 790 | 0.0004 | - |
|
| 343 |
-
| 8.3333 | 800 | 0.0004 | - |
|
| 344 |
-
| 8.4375 | 810 | 0.0004 | - |
|
| 345 |
-
| 8.5417 | 820 | 0.0004 | - |
|
| 346 |
-
| 8.6458 | 830 | 0.0004 | - |
|
| 347 |
-
| 8.75 | 840 | 0.0004 | - |
|
| 348 |
-
| 8.8542 | 850 | 0.0004 | - |
|
| 349 |
-
| 8.9583 | 860 | 0.0004 | - |
|
| 350 |
-
| 9.0625 | 870 | 0.0004 | - |
|
| 351 |
-
| 9.1667 | 880 | 0.0004 | - |
|
| 352 |
-
| 9.2708 | 890 | 0.0004 | - |
|
| 353 |
-
| 9.375 | 900 | 0.0004 | - |
|
| 354 |
-
| 9.4792 | 910 | 0.0004 | - |
|
| 355 |
-
| 9.5833 | 920 | 0.0004 | - |
|
| 356 |
-
| 9.6875 | 930 | 0.0004 | - |
|
| 357 |
-
| 9.7917 | 940 | 0.0004 | - |
|
| 358 |
-
| 9.8958 | 950 | 0.0004 | - |
|
| 359 |
-
| 10.0 | 960 | 0.0004 | - |
|
| 360 |
-
| 0.0046 | 1 | 0.049 | - |
|
| 361 |
-
| 0.4630 | 100 | 0.035 | - |
|
| 362 |
-
| 0.9259 | 200 | 0.0097 | - |
|
| 363 |
-
| 1.3889 | 300 | 0.0007 | - |
|
| 364 |
-
| 1.8519 | 400 | 0.0004 | - |
|
| 365 |
-
| 2.3148 | 500 | 0.0004 | - |
|
| 366 |
-
| 2.7778 | 600 | 0.0004 | - |
|
| 367 |
-
| 3.2407 | 700 | 0.0004 | - |
|
| 368 |
-
| 3.7037 | 800 | 0.0004 | - |
|
| 369 |
-
| 4.1667 | 900 | 0.0004 | - |
|
| 370 |
-
| 4.6296 | 1000 | 0.0003 | - |
|
| 371 |
-
| 5.0926 | 1100 | 0.0003 | - |
|
| 372 |
-
| 5.5556 | 1200 | 0.0003 | - |
|
| 373 |
-
| 6.0185 | 1300 | 0.0003 | - |
|
| 374 |
-
| 6.4815 | 1400 | 0.0003 | - |
|
| 375 |
-
| 6.9444 | 1500 | 0.0003 | - |
|
| 376 |
-
| 7.4074 | 1600 | 0.0003 | - |
|
| 377 |
-
| 7.8704 | 1700 | 0.0003 | - |
|
| 378 |
-
| 8.3333 | 1800 | 0.0003 | - |
|
| 379 |
-
| 8.7963 | 1900 | 0.0003 | - |
|
| 380 |
-
| 9.2593 | 2000 | 0.0003 | - |
|
| 381 |
-
| 9.7222 | 2100 | 0.0003 | - |
|
| 382 |
|
| 383 |
### Framework Versions
|
| 384 |
- Python: 3.11.0
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: BAAI/bge-m3
|
| 3 |
library_name: setfit
|
| 4 |
metrics:
|
| 5 |
- accuracy
|
|
|
|
| 18 |
- text: Konstrukcja łóżka piętrowego jest wadliwa, elementy nie pasują do siebie.
|
| 19 |
inference: true
|
| 20 |
model-index:
|
| 21 |
+
- name: SetFit with BAAI/bge-m3
|
| 22 |
results:
|
| 23 |
- task:
|
| 24 |
type: text-classification
|
|
|
|
| 29 |
split: test
|
| 30 |
metrics:
|
| 31 |
- type: accuracy
|
| 32 |
+
value: 0.8632478632478633
|
| 33 |
name: Accuracy
|
| 34 |
---
|
| 35 |
|
| 36 |
+
# SetFit with BAAI/bge-m3
|
| 37 |
|
| 38 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
|
| 39 |
|
| 40 |
The model has been trained using an efficient few-shot learning technique that involves:
|
| 41 |
|
|
|
|
| 46 |
|
| 47 |
### Model Description
|
| 48 |
- **Model Type:** SetFit
|
| 49 |
+
- **Sentence Transformer body:** [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3)
|
| 50 |
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
| 51 |
+
- **Maximum Sequence Length:** 8192 tokens
|
| 52 |
- **Number of Classes:** 4 classes
|
| 53 |
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
| 54 |
<!-- - **Language:** Unknown -->
|
|
|
|
| 61 |
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
| 62 |
|
| 63 |
### Model Labels
|
| 64 |
+
| Label | Examples |
|
| 65 |
+
|:---------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
| 66 |
+
| błędny montaż | <ul><li>'Pojemnik pod łóżkiem jest źle zamontowany i nie otwiera się.'</li><li>'Nogi komody nowoczesnej są źle przymocowane i komoda jest niestabilna.'</li><li>'Oświetlenie w witrynie z oświetleniem jest źle podłączone i nie działa.'</li></ul> |
|
| 67 |
+
| wady fabryczne | <ul><li>'Front szafki RTV jest uszkodzony, posiada wgniecenie i rysę.'</li><li>'Tapicerka krzesła jest rozdarcia.'</li><li>'Blat biurka narożnego ma pęknięcie, widoczne gołym okiem.'</li></ul> |
|
| 68 |
+
| niezgodność towaru z zamówieniem | <ul><li>'Materiał szafy Prosty jest inny niż ten, który został zamówiony.'</li><li>'Regał narożny ma inne wymiary niż te, które zostały podane w zamówieniu.'</li><li>'Zamówiony fotel bujany miał zawierać poduszkę, której nie ma w przesyłce. Potwierdzenie zamówienia wskazuje na dołączoną poduszkę.'</li></ul> |
|
| 69 |
+
| uszkodzenia | <ul><li>'Szyba stolika kawowego Minimal jest pęknięta.'</li><li>'Prowadnice szuflad w szafie wnękowej Max są uszkodzone.'</li><li>'Drzwiczki szafy na buty Shoes są uszkodzone.'</li></ul> |
|
| 70 |
|
| 71 |
## Evaluation
|
| 72 |
|
| 73 |
### Metrics
|
| 74 |
| Label | Accuracy |
|
| 75 |
|:--------|:---------|
|
| 76 |
+
| **all** | 0.8632 |
|
| 77 |
|
| 78 |
## Uses
|
| 79 |
|
|
|
|
| 123 |
## Training Details
|
| 124 |
|
| 125 |
### Training Set Metrics
|
| 126 |
+
| Training set | Min | Median | Max |
|
| 127 |
+
|:-------------|:----|:-------|:----|
|
| 128 |
+
| Word count | 4 | 10.0 | 20 |
|
| 129 |
|
| 130 |
| Label | Training Sample Count |
|
| 131 |
|:---------------------------------|:----------------------|
|
| 132 |
+
| uszkodzenia | 8 |
|
| 133 |
+
| wady fabryczne | 8 |
|
| 134 |
+
| niezgodność towaru z zamówieniem | 8 |
|
| 135 |
+
| błędny montaż | 8 |
|
| 136 |
|
| 137 |
### Training Hyperparameters
|
| 138 |
- batch_size: (32, 32)
|
|
|
|
| 155 |
### Training Results
|
| 156 |
| Epoch | Step | Training Loss | Validation Loss |
|
| 157 |
|:------:|:----:|:-------------:|:---------------:|
|
| 158 |
+
| 0.0417 | 1 | 0.1938 | - |
|
| 159 |
+
| 4.1667 | 100 | 0.0392 | - |
|
| 160 |
+
| 8.3333 | 200 | 0.0011 | - |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 161 |
|
| 162 |
### Framework Versions
|
| 163 |
- Python: 3.11.0
|
config.json
CHANGED
|
@@ -1,31 +1,28 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "BAAI/bge-
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
|
| 7 |
"classifier_dropout": null,
|
|
|
|
| 8 |
"hidden_act": "gelu",
|
| 9 |
"hidden_dropout_prob": 0.1,
|
| 10 |
-
"hidden_size":
|
| 11 |
-
"id2label": {
|
| 12 |
-
"0": "LABEL_0"
|
| 13 |
-
},
|
| 14 |
"initializer_range": 0.02,
|
| 15 |
-
"intermediate_size":
|
| 16 |
-
"
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
"
|
| 20 |
-
"
|
| 21 |
-
"
|
| 22 |
-
"
|
| 23 |
-
"num_hidden_layers": 12,
|
| 24 |
-
"pad_token_id": 0,
|
| 25 |
"position_embedding_type": "absolute",
|
| 26 |
"torch_dtype": "float32",
|
| 27 |
"transformers_version": "4.44.2",
|
| 28 |
-
"type_vocab_size":
|
| 29 |
"use_cache": true,
|
| 30 |
-
"vocab_size":
|
| 31 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "BAAI/bge-m3",
|
| 3 |
"architectures": [
|
| 4 |
+
"XLMRobertaModel"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
"hidden_act": "gelu",
|
| 11 |
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
|
|
|
|
|
|
|
|
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 4096,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 8194,
|
| 17 |
+
"model_type": "xlm-roberta",
|
| 18 |
+
"num_attention_heads": 16,
|
| 19 |
+
"num_hidden_layers": 24,
|
| 20 |
+
"output_past": true,
|
| 21 |
+
"pad_token_id": 1,
|
|
|
|
|
|
|
| 22 |
"position_embedding_type": "absolute",
|
| 23 |
"torch_dtype": "float32",
|
| 24 |
"transformers_version": "4.44.2",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
"use_cache": true,
|
| 27 |
+
"vocab_size": 250002
|
| 28 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5afa630367ef1327aff1a6dcf42118c89e56361a8ae8af02fa88cd8ef7787623
|
| 3 |
+
size 2271064456
|
model_head.pkl
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b59f9f198aa646bc719aeaace8f57453440fefc37dab054d4a9f53ee932ad7f7
|
| 3 |
+
size 33671
|
sentence_bert_config.json
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"max_seq_length":
|
| 3 |
-
"do_lower_case":
|
| 4 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"max_seq_length": 8192,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
}
|
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
special_tokens_map.json
CHANGED
|
@@ -1,34 +1,48 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"cls_token": {
|
| 3 |
-
"content": "
|
| 4 |
"lstrip": false,
|
| 5 |
"normalized": false,
|
| 6 |
"rstrip": false,
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
-
"
|
| 10 |
-
"content": "
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
"pad_token": {
|
| 17 |
-
"content": "
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
| 21 |
"single_word": false
|
| 22 |
},
|
| 23 |
"sep_token": {
|
| 24 |
-
"content": "
|
| 25 |
"lstrip": false,
|
| 26 |
"normalized": false,
|
| 27 |
"rstrip": false,
|
| 28 |
"single_word": false
|
| 29 |
},
|
| 30 |
"unk_token": {
|
| 31 |
-
"content": "
|
| 32 |
"lstrip": false,
|
| 33 |
"normalized": false,
|
| 34 |
"rstrip": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
| 21 |
"single_word": false
|
| 22 |
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
"lstrip": false,
|
| 33 |
"normalized": false,
|
| 34 |
"rstrip": false,
|
| 35 |
"single_word": false
|
| 36 |
},
|
| 37 |
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
"lstrip": false,
|
| 40 |
"normalized": false,
|
| 41 |
"rstrip": false,
|
| 42 |
"single_word": false
|
| 43 |
},
|
| 44 |
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
"lstrip": false,
|
| 47 |
"normalized": false,
|
| 48 |
"rstrip": false,
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,57 +1,55 @@
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
-
"content": "
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
| 7 |
"rstrip": false,
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
-
"
|
| 12 |
-
"content": "
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|
| 15 |
"rstrip": false,
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
-
"
|
| 20 |
-
"content": "
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
-
"
|
| 28 |
-
"content": "
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
-
"
|
| 36 |
-
"content": "
|
| 37 |
-
"lstrip":
|
| 38 |
"normalized": false,
|
| 39 |
"rstrip": false,
|
| 40 |
"single_word": false,
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
|
|
|
| 44 |
"clean_up_tokenization_spaces": true,
|
| 45 |
-
"cls_token": "
|
| 46 |
-
"
|
| 47 |
-
"
|
| 48 |
-
"
|
| 49 |
-
"
|
| 50 |
-
"
|
| 51 |
-
"
|
| 52 |
-
"
|
| 53 |
-
"
|
| 54 |
-
"tokenize_chinese_chars": true,
|
| 55 |
-
"tokenizer_class": "BertTokenizer",
|
| 56 |
-
"unk_token": "[UNK]"
|
| 57 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
| 7 |
"rstrip": false,
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|
| 15 |
"rstrip": false,
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
+
"250001": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
"normalized": false,
|
| 39 |
"rstrip": false,
|
| 40 |
"single_word": false,
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"mask_token": "<mask>",
|
| 49 |
+
"model_max_length": 8192,
|
| 50 |
+
"pad_token": "<pad>",
|
| 51 |
+
"sep_token": "</s>",
|
| 52 |
+
"sp_model_kwargs": {},
|
| 53 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 54 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
| 55 |
}
|