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
cacf0c7
•
1 Parent(s): 1ce14f1

Add SetFit model

Browse files
Files changed (5) hide show
  1. README.md +100 -77
  2. config.json +1 -1
  3. config_setfit.json +2 -2
  4. model.safetensors +1 -1
  5. model_head.pkl +1 -1
README.md CHANGED
@@ -137,8 +137,8 @@ preds = model("What is the purpose of the message posted by the CR?")
137
  | very_semantic | 33 |
138
 
139
  ### Training Hyperparameters
140
- - batch_size: (8, 8)
141
- - num_epochs: (3, 3)
142
  - max_steps: -1
143
  - sampling_strategy: oversampling
144
  - body_learning_rate: (2e-05, 1e-05)
@@ -156,81 +156,104 @@ preds = model("What is the purpose of the message posted by the CR?")
156
  ### Training Results
157
  | Epoch | Step | Training Loss | Validation Loss |
158
  |:-------:|:--------:|:-------------:|:---------------:|
159
- | 0.0008 | 1 | 0.4237 | - |
160
- | 0.0417 | 50 | 0.2917 | - |
161
- | 0.0834 | 100 | 0.1835 | - |
162
- | 0.1251 | 150 | 0.3215 | - |
163
- | 0.1668 | 200 | 0.2299 | - |
164
- | 0.2085 | 250 | 0.2595 | - |
165
- | 0.2502 | 300 | 0.3193 | - |
166
- | 0.2919 | 350 | 0.2288 | - |
167
- | 0.3336 | 400 | 0.2947 | - |
168
- | 0.3753 | 450 | 0.1171 | - |
169
- | 0.4170 | 500 | 0.1442 | - |
170
- | 0.4587 | 550 | 0.1859 | - |
171
- | 0.5004 | 600 | 0.1959 | - |
172
- | 0.5421 | 650 | 0.2797 | - |
173
- | 0.5838 | 700 | 0.2079 | - |
174
- | 0.6255 | 750 | 0.2706 | - |
175
- | 0.6672 | 800 | 0.1956 | - |
176
- | 0.7089 | 850 | 0.0833 | - |
177
- | 0.7506 | 900 | 0.1421 | - |
178
- | 0.7923 | 950 | 0.2345 | - |
179
- | 0.8340 | 1000 | 0.1347 | - |
180
- | 0.8757 | 1050 | 0.241 | - |
181
- | 0.9174 | 1100 | 0.133 | - |
182
- | 0.9591 | 1150 | 0.1041 | - |
183
- | **1.0** | **1199** | **-** | **0.3562** |
184
- | 1.0008 | 1200 | 0.0837 | - |
185
- | 1.0425 | 1250 | 0.1566 | - |
186
- | 1.0842 | 1300 | 0.2101 | - |
187
- | 1.1259 | 1350 | 0.0496 | - |
188
- | 1.1676 | 1400 | 0.063 | - |
189
- | 1.2093 | 1450 | 0.149 | - |
190
- | 1.2510 | 1500 | 0.038 | - |
191
- | 1.2927 | 1550 | 0.0504 | - |
192
- | 1.3344 | 1600 | 0.0679 | - |
193
- | 1.3761 | 1650 | 0.1699 | - |
194
- | 1.4178 | 1700 | 0.1293 | - |
195
- | 1.4595 | 1750 | 0.1083 | - |
196
- | 1.5013 | 1800 | 0.2044 | - |
197
- | 1.5430 | 1850 | 0.1267 | - |
198
- | 1.5847 | 1900 | 0.0842 | - |
199
- | 1.6264 | 1950 | 0.1126 | - |
200
- | 1.6681 | 2000 | 0.0544 | - |
201
- | 1.7098 | 2050 | 0.143 | - |
202
- | 1.7515 | 2100 | 0.08 | - |
203
- | 1.7932 | 2150 | 0.1103 | - |
204
- | 1.8349 | 2200 | 0.1768 | - |
205
- | 1.8766 | 2250 | 0.1639 | - |
206
- | 1.9183 | 2300 | 0.1637 | - |
207
- | 1.9600 | 2350 | 0.1637 | - |
208
- | 2.0 | 2398 | - | 0.3682 |
209
- | 2.0017 | 2400 | 0.2938 | - |
210
- | 2.0434 | 2450 | 0.0808 | - |
211
- | 2.0851 | 2500 | 0.0788 | - |
212
- | 2.1268 | 2550 | 0.2187 | - |
213
- | 2.1685 | 2600 | 0.0701 | - |
214
- | 2.2102 | 2650 | 0.0385 | - |
215
- | 2.2519 | 2700 | 0.135 | - |
216
- | 2.2936 | 2750 | 0.2276 | - |
217
- | 2.3353 | 2800 | 0.2203 | - |
218
- | 2.3770 | 2850 | 0.0029 | - |
219
- | 2.4187 | 2900 | 0.1855 | - |
220
- | 2.4604 | 2950 | 0.1278 | - |
221
- | 2.5021 | 3000 | 0.0487 | - |
222
- | 2.5438 | 3050 | 0.0404 | - |
223
- | 2.5855 | 3100 | 0.1158 | - |
224
- | 2.6272 | 3150 | 0.1354 | - |
225
- | 2.6689 | 3200 | 0.1633 | - |
226
- | 2.7106 | 3250 | 0.1484 | - |
227
- | 2.7523 | 3300 | 0.1146 | - |
228
- | 2.7940 | 3350 | 0.1437 | - |
229
- | 2.8357 | 3400 | 0.0948 | - |
230
- | 2.8774 | 3450 | 0.0833 | - |
231
- | 2.9191 | 3500 | 0.0668 | - |
232
- | 2.9608 | 3550 | 0.1687 | - |
233
- | 3.0 | 3597 | - | 0.3651 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
234
 
235
  * The bold row denotes the saved checkpoint.
236
  ### Framework Versions
 
137
  | very_semantic | 33 |
138
 
139
  ### Training Hyperparameters
140
+ - batch_size: (4, 4)
141
+ - num_epochs: (2, 2)
142
  - max_steps: -1
143
  - sampling_strategy: oversampling
144
  - body_learning_rate: (2e-05, 1e-05)
 
156
  ### Training Results
157
  | Epoch | Step | Training Loss | Validation Loss |
158
  |:-------:|:--------:|:-------------:|:---------------:|
159
+ | 0.0004 | 1 | 0.4883 | - |
160
+ | 0.0209 | 50 | 0.3738 | - |
161
+ | 0.0417 | 100 | 0.2192 | - |
162
+ | 0.0626 | 150 | 0.1503 | - |
163
+ | 0.0834 | 200 | 0.1514 | - |
164
+ | 0.1043 | 250 | 0.1829 | - |
165
+ | 0.1251 | 300 | 0.4191 | - |
166
+ | 0.1460 | 350 | 0.2136 | - |
167
+ | 0.1668 | 400 | 0.1847 | - |
168
+ | 0.1877 | 450 | 0.1681 | - |
169
+ | 0.2085 | 500 | 0.222 | - |
170
+ | 0.2294 | 550 | 0.0397 | - |
171
+ | 0.2502 | 600 | 0.2626 | - |
172
+ | 0.2711 | 650 | 0.1343 | - |
173
+ | 0.2919 | 700 | 0.1769 | - |
174
+ | 0.3128 | 750 | 0.1704 | - |
175
+ | 0.3336 | 800 | 0.401 | - |
176
+ | 0.3545 | 850 | 0.1405 | - |
177
+ | 0.3753 | 900 | 0.1892 | - |
178
+ | 0.3962 | 950 | 0.1444 | - |
179
+ | 0.4170 | 1000 | 0.2337 | - |
180
+ | 0.4379 | 1050 | 0.1848 | - |
181
+ | 0.4587 | 1100 | 0.0601 | - |
182
+ | 0.4796 | 1150 | 0.2467 | - |
183
+ | 0.5004 | 1200 | 0.1829 | - |
184
+ | 0.5213 | 1250 | 0.1695 | - |
185
+ | 0.5421 | 1300 | 0.3892 | - |
186
+ | 0.5630 | 1350 | 0.1408 | - |
187
+ | 0.5838 | 1400 | 0.0506 | - |
188
+ | 0.6047 | 1450 | 0.1835 | - |
189
+ | 0.6255 | 1500 | 0.3284 | - |
190
+ | 0.6464 | 1550 | 0.1797 | - |
191
+ | 0.6672 | 1600 | 0.1118 | - |
192
+ | 0.6881 | 1650 | 0.1502 | - |
193
+ | 0.7089 | 1700 | 0.112 | - |
194
+ | 0.7298 | 1750 | 0.0401 | - |
195
+ | 0.7506 | 1800 | 0.117 | - |
196
+ | 0.7715 | 1850 | 0.1287 | - |
197
+ | 0.7923 | 1900 | 0.0623 | - |
198
+ | 0.8132 | 1950 | 0.2128 | - |
199
+ | 0.8340 | 2000 | 0.1542 | - |
200
+ | 0.8549 | 2050 | 0.1774 | - |
201
+ | 0.8757 | 2100 | 0.3252 | - |
202
+ | 0.8966 | 2150 | 0.0152 | - |
203
+ | 0.9174 | 2200 | 0.0539 | - |
204
+ | 0.9383 | 2250 | 0.0047 | - |
205
+ | 0.9591 | 2300 | 0.1232 | - |
206
+ | 0.9800 | 2350 | 0.3466 | - |
207
+ | **1.0** | **2398** | **-** | **0.3644** |
208
+ | 1.0008 | 2400 | 0.0296 | - |
209
+ | 1.0217 | 2450 | 0.3459 | - |
210
+ | 1.0425 | 2500 | 0.0867 | - |
211
+ | 1.0634 | 2550 | 0.1343 | - |
212
+ | 1.0842 | 2600 | 0.2074 | - |
213
+ | 1.1051 | 2650 | 0.0052 | - |
214
+ | 1.1259 | 2700 | 0.0548 | - |
215
+ | 1.1468 | 2750 | 0.0441 | - |
216
+ | 1.1676 | 2800 | 0.0821 | - |
217
+ | 1.1885 | 2850 | 0.0546 | - |
218
+ | 1.2093 | 2900 | 0.1286 | - |
219
+ | 1.2302 | 2950 | 0.1222 | - |
220
+ | 1.2510 | 3000 | 0.0227 | - |
221
+ | 1.2719 | 3050 | 0.3011 | - |
222
+ | 1.2927 | 3100 | 0.018 | - |
223
+ | 1.3136 | 3150 | 0.0581 | - |
224
+ | 1.3344 | 3200 | 0.0485 | - |
225
+ | 1.3553 | 3250 | 0.2369 | - |
226
+ | 1.3761 | 3300 | 0.1681 | - |
227
+ | 1.3970 | 3350 | 0.1289 | - |
228
+ | 1.4178 | 3400 | 0.1664 | - |
229
+ | 1.4387 | 3450 | 0.1467 | - |
230
+ | 1.4595 | 3500 | 0.1399 | - |
231
+ | 1.4804 | 3550 | 0.3045 | - |
232
+ | 1.5013 | 3600 | 0.2155 | - |
233
+ | 1.5221 | 3650 | 0.061 | - |
234
+ | 1.5430 | 3700 | 0.0787 | - |
235
+ | 1.5638 | 3750 | 0.3649 | - |
236
+ | 1.5847 | 3800 | 0.1202 | - |
237
+ | 1.6055 | 3850 | 0.1004 | - |
238
+ | 1.6264 | 3900 | 0.154 | - |
239
+ | 1.6472 | 3950 | 0.0944 | - |
240
+ | 1.6681 | 4000 | 0.0004 | - |
241
+ | 1.6889 | 4050 | 0.1843 | - |
242
+ | 1.7098 | 4100 | 0.2233 | - |
243
+ | 1.7306 | 4150 | 0.2203 | - |
244
+ | 1.7515 | 4200 | 0.0986 | - |
245
+ | 1.7723 | 4250 | 0.2295 | - |
246
+ | 1.7932 | 4300 | 0.1763 | - |
247
+ | 1.8140 | 4350 | 0.3487 | - |
248
+ | 1.8349 | 4400 | 0.3285 | - |
249
+ | 1.8557 | 4450 | 0.0152 | - |
250
+ | 1.8766 | 4500 | 0.1108 | - |
251
+ | 1.8974 | 4550 | 0.2416 | - |
252
+ | 1.9183 | 4600 | 0.0476 | - |
253
+ | 1.9391 | 4650 | 0.2929 | - |
254
+ | 1.9600 | 4700 | 0.1006 | - |
255
+ | 1.9808 | 4750 | 0.0925 | - |
256
+ | 2.0 | 4796 | - | 0.3669 |
257
 
258
  * The bold row denotes the saved checkpoint.
259
  ### Framework Versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "checkpoints/step_1199",
3
  "architectures": [
4
  "BertModel"
5
  ],
 
1
  {
2
+ "_name_or_path": "checkpoints/step_2398",
3
  "architectures": [
4
  "BertModel"
5
  ],
config_setfit.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "normalize_embeddings": false,
3
  "labels": [
4
  "lexical",
5
  "semantic",
6
  "very_lexical",
7
  "very_semantic"
8
- ]
 
9
  }
 
1
  {
 
2
  "labels": [
3
  "lexical",
4
  "semantic",
5
  "very_lexical",
6
  "very_semantic"
7
+ ],
8
+ "normalize_embeddings": false
9
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54e1f2ecdb4d01b6727aa7c7082233ca8c6ed1ad2689e8555996d2feeeeb4e57
3
  size 90864192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a7c4c1a22e1f5dd8d9c84e0edc1c73e605dc3db206243cc7071620ed767ce86
3
  size 90864192
model_head.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:178c77f056f085ee38b4a6c61f668e1dedcdd7a98a79ec3d6055de6ef300abf3
3
  size 13367
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b4df6de02dd567aa355857d504795aa3ed2e9d34cd9f5ad0137eb3a1292e64b
3
  size 13367