Hugging Face's logo

yaniseuranova
/
setfit-rag-hybrid-search-query-router-test

Text Classification
setfit
Safetensors
sentence-transformers
bert
generated_from_setfit_trainer
Eval Results
Model card Files Community
yaniseuranova commited on
Commit
c999004
•
1 Parent(s): 5b57d04

Add SetFit model

Browse files
Files changed (5) hide show
  1. README.md +83 -23
  2. config.json +1 -1
  3. config_setfit.json +2 -2
  4. model.safetensors +1 -1
  5. model_head.pkl +2 -2
README.md CHANGED
@@ -133,7 +133,7 @@ preds = model("What is the purpose of setting up a CUPS on a server?")
133
  | semantic | 118 |
134
 
135
  ### Training Hyperparameters
136
- - batch_size: (16, 16)
137
  - num_epochs: (1, 1)
138
  - max_steps: -1
139
  - sampling_strategy: oversampling
@@ -152,28 +152,88 @@ preds = model("What is the purpose of setting up a CUPS on a server?")
152
  ### Training Results
153
  | Epoch | Step | Training Loss | Validation Loss |
154
  |:-------:|:--------:|:-------------:|:---------------:|
155
- | 0.0010 | 1 | 0.4175 | - |
156
- | 0.0499 | 50 | 0.2952 | - |
157
- | 0.0998 | 100 | 0.202 | - |
158
- | 0.1497 | 150 | 0.0386 | - |
159
- | 0.1996 | 200 | 0.0019 | - |
160
- | 0.2495 | 250 | 0.006 | - |
161
- | 0.2994 | 300 | 0.0006 | - |
162
- | 0.3493 | 350 | 0.0016 | - |
163
- | 0.3992 | 400 | 0.0006 | - |
164
- | 0.4491 | 450 | 0.0005 | - |
165
- | 0.4990 | 500 | 0.0004 | - |
166
- | 0.5489 | 550 | 0.0004 | - |
167
- | 0.5988 | 600 | 0.0006 | - |
168
- | 0.6487 | 650 | 0.0003 | - |
169
- | 0.6986 | 700 | 0.0003 | - |
170
- | 0.7485 | 750 | 0.0003 | - |
171
- | 0.7984 | 800 | 0.0007 | - |
172
- | 0.8483 | 850 | 0.0005 | - |
173
- | 0.8982 | 900 | 0.0005 | - |
174
- | 0.9481 | 950 | 0.0003 | - |
175
- | 0.9980 | 1000 | 0.0002 | - |
176
- | **1.0** | **1002** | **-** | **0.1776** |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
177
 
178
  * The bold row denotes the saved checkpoint.
179
  ### Framework Versions
 
133
  | semantic | 118 |
134
 
135
  ### Training Hyperparameters
136
+ - batch_size: (4, 4)
137
  - num_epochs: (1, 1)
138
  - max_steps: -1
139
  - sampling_strategy: oversampling
 
152
  ### Training Results
153
  | Epoch | Step | Training Loss | Validation Loss |
154
  |:-------:|:--------:|:-------------:|:---------------:|
155
+ | 0.0002 | 1 | 0.4185 | - |
156
+ | 0.0125 | 50 | 0.3825 | - |
157
+ | 0.0250 | 100 | 0.1752 | - |
158
+ | 0.0374 | 150 | 0.1581 | - |
159
+ | 0.0499 | 200 | 0.2404 | - |
160
+ | 0.0624 | 250 | 0.1858 | - |
161
+ | 0.0749 | 300 | 0.3777 | - |
162
+ | 0.0874 | 350 | 0.0112 | - |
163
+ | 0.0999 | 400 | 0.0449 | - |
164
+ | 0.1123 | 450 | 0.0019 | - |
165
+ | 0.1248 | 500 | 0.0019 | - |
166
+ | 0.1373 | 550 | 0.0007 | - |
167
+ | 0.1498 | 600 | 0.0006 | - |
168
+ | 0.1623 | 650 | 0.0012 | - |
169
+ | 0.1747 | 700 | 0.0007 | - |
170
+ | 0.1872 | 750 | 0.001 | - |
171
+ | 0.1997 | 800 | 0.0004 | - |
172
+ | 0.2122 | 850 | 0.0001 | - |
173
+ | 0.2247 | 900 | 0.0002 | - |
174
+ | 0.2371 | 950 | 0.0001 | - |
175
+ | 0.2496 | 1000 | 0.0014 | - |
176
+ | 0.2621 | 1050 | 0.0001 | - |
177
+ | 0.2746 | 1100 | 0.0001 | - |
178
+ | 0.2871 | 1150 | 0.0001 | - |
179
+ | 0.2996 | 1200 | 0.0001 | - |
180
+ | 0.3120 | 1250 | 0.0001 | - |
181
+ | 0.3245 | 1300 | 0.0002 | - |
182
+ | 0.3370 | 1350 | 0.0001 | - |
183
+ | 0.3495 | 1400 | 0.0003 | - |
184
+ | 0.3620 | 1450 | 0.0003 | - |
185
+ | 0.3744 | 1500 | 0.0001 | - |
186
+ | 0.3869 | 1550 | 0.0005 | - |
187
+ | 0.3994 | 1600 | 0.0002 | - |
188
+ | 0.4119 | 1650 | 0.0002 | - |
189
+ | 0.4244 | 1700 | 0.0002 | - |
190
+ | 0.4368 | 1750 | 0.0001 | - |
191
+ | 0.4493 | 1800 | 0.0001 | - |
192
+ | 0.4618 | 1850 | 0.0002 | - |
193
+ | 0.4743 | 1900 | 0.0001 | - |
194
+ | 0.4868 | 1950 | 0.0002 | - |
195
+ | 0.4993 | 2000 | 0.0002 | - |
196
+ | 0.5117 | 2050 | 0.0001 | - |
197
+ | 0.5242 | 2100 | 0.0001 | - |
198
+ | 0.5367 | 2150 | 0.0001 | - |
199
+ | 0.5492 | 2200 | 0.0001 | - |
200
+ | 0.5617 | 2250 | 0.0002 | - |
201
+ | 0.5741 | 2300 | 0.0001 | - |
202
+ | 0.5866 | 2350 | 0.0001 | - |
203
+ | 0.5991 | 2400 | 0.0001 | - |
204
+ | 0.6116 | 2450 | 0.0001 | - |
205
+ | 0.6241 | 2500 | 0.0002 | - |
206
+ | 0.6365 | 2550 | 0.0001 | - |
207
+ | 0.6490 | 2600 | 0.0001 | - |
208
+ | 0.6615 | 2650 | 0.0001 | - |
209
+ | 0.6740 | 2700 | 0.0001 | - |
210
+ | 0.6865 | 2750 | 0.0001 | - |
211
+ | 0.6990 | 2800 | 0.0001 | - |
212
+ | 0.7114 | 2850 | 0.0001 | - |
213
+ | 0.7239 | 2900 | 0.0001 | - |
214
+ | 0.7364 | 2950 | 0.0001 | - |
215
+ | 0.7489 | 3000 | 0.0001 | - |
216
+ | 0.7614 | 3050 | 0.0001 | - |
217
+ | 0.7738 | 3100 | 0.0001 | - |
218
+ | 0.7863 | 3150 | 0.0001 | - |
219
+ | 0.7988 | 3200 | 0.0002 | - |
220
+ | 0.8113 | 3250 | 0.0001 | - |
221
+ | 0.8238 | 3300 | 0.0001 | - |
222
+ | 0.8362 | 3350 | 0.0001 | - |
223
+ | 0.8487 | 3400 | 0.0001 | - |
224
+ | 0.8612 | 3450 | 0.0 | - |
225
+ | 0.8737 | 3500 | 0.0001 | - |
226
+ | 0.8862 | 3550 | 0.0 | - |
227
+ | 0.8987 | 3600 | 0.0001 | - |
228
+ | 0.9111 | 3650 | 0.0002 | - |
229
+ | 0.9236 | 3700 | 0.0001 | - |
230
+ | 0.9361 | 3750 | 0.0001 | - |
231
+ | 0.9486 | 3800 | 0.0 | - |
232
+ | 0.9611 | 3850 | 0.0001 | - |
233
+ | 0.9735 | 3900 | 0.0001 | - |
234
+ | 0.9860 | 3950 | 0.0001 | - |
235
+ | 0.9985 | 4000 | 0.0 | - |
236
+ | **1.0** | **4006** | **-** | **0.1768** |
237
 
238
  * The bold row denotes the saved checkpoint.
239
  ### Framework Versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "checkpoints/step_1002",
3
  "architectures": [
4
  "BertModel"
5
  ],
 
1
  {
2
+ "_name_or_path": "checkpoints/step_4006",
3
  "architectures": [
4
  "BertModel"
5
  ],
config_setfit.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "normalize_embeddings": false,
3
  "labels": [
4
  "lexical",
5
  "semantic"
6
- ]
 
7
  }
 
1
  {
 
2
  "labels": [
3
  "lexical",
4
  "semantic"
5
+ ],
6
+ "normalize_embeddings": false
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:630b2cf590a4f3b628a5743400cf88b7193076a1353777f3aa52894abfdcb70b
3
  size 90864192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d670eaf190b9fca2d5d609ed30e6667192002e954dd8d67a4b7e75e08d04f8fc
3
  size 90864192
model_head.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eab7599a53190410f999e2a92d196a82982bb326338557b3bec36f4bb2e97bc3
3
- size 147860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a67909d634f239bbae8ad95596d5d32908f41b8c6bf64c4daafd58f8e0f386ad
3
+ size 3983