Hugging Face's logo

keivan
/
Setfit_bert-zwnj-wnli-mean-tokens

Text Classification
setfit
Safetensors
sentence-transformers
bert
generated_from_setfit_trainer
Eval Results
Model card Files Community
keivan commited on
Commit
299928b
·
1 Parent(s): 67ddadb

Add SetFit model

Browse files
Files changed (3) hide show
  1. README.md +29 -44
  2. model.safetensors +1 -1
  3. model_head.pkl +1 -1
README.md CHANGED
@@ -152,7 +152,7 @@ preds = model("خوبه ولی کیفیت ظروف مناسب نیست")
152
 
153
  ### Training Hyperparameters
154
  - batch_size: (8, 8)
155
- - num_epochs: (3, 3)
156
  - max_steps: -1
157
  - sampling_strategy: oversampling
158
  - body_learning_rate: (2e-05, 1e-05)
@@ -171,49 +171,34 @@ preds = model("خوبه ولی کیفیت ظروف مناسب نیست")
171
  | Epoch | Step | Training Loss | Validation Loss |
172
  |:-------:|:-------:|:-------------:|:---------------:|
173
  | 0.0015 | 1 | 0.306 | - |
174
- | 0.0742 | 50 | 0.2519 | - |
175
- | 0.1484 | 100 | 0.2641 | - |
176
- | 0.2226 | 150 | 0.093 | - |
177
- | 0.2967 | 200 | 0.0394 | - |
178
- | 0.3709 | 250 | 0.0618 | - |
179
- | 0.4451 | 300 | 0.0083 | - |
180
- | 0.5193 | 350 | 0.0301 | - |
181
- | 0.5935 | 400 | 0.007 | - |
182
- | 0.6677 | 450 | 0.0038 | - |
183
- | 0.7418 | 500 | 0.0018 | - |
184
- | 0.8160 | 550 | 0.0027 | - |
185
- | 0.8902 | 600 | 0.0021 | - |
186
- | 0.9644 | 650 | 0.0006 | - |
187
- | **1.0** | **674** | **-** | **0.0343** |
188
- | 1.0386 | 700 | 0.0006 | - |
189
- | 1.1128 | 750 | 0.0009 | - |
190
- | 1.1869 | 800 | 0.0002 | - |
191
- | 1.2611 | 850 | 0.0031 | - |
192
- | 1.3353 | 900 | 0.0011 | - |
193
- | 1.4095 | 950 | 0.0008 | - |
194
- | 1.4837 | 1000 | 0.0005 | - |
195
- | 1.5579 | 1050 | 0.0004 | - |
196
- | 1.6320 | 1100 | 0.0005 | - |
197
- | 1.7062 | 1150 | 0.0005 | - |
198
- | 1.7804 | 1200 | 0.0003 | - |
199
- | 1.8546 | 1250 | 0.0002 | - |
200
- | 1.9288 | 1300 | 0.0006 | - |
201
- | 2.0 | 1348 | - | 0.0359 |
202
- | 2.0030 | 1350 | 0.0003 | - |
203
- | 2.0772 | 1400 | 0.0016 | - |
204
- | 2.1513 | 1450 | 0.0002 | - |
205
- | 2.2255 | 1500 | 0.0002 | - |
206
- | 2.2997 | 1550 | 0.0003 | - |
207
- | 2.3739 | 1600 | 0.0011 | - |
208
- | 2.4481 | 1650 | 0.0003 | - |
209
- | 2.5223 | 1700 | 0.0002 | - |
210
- | 2.5964 | 1750 | 0.0004 | - |
211
- | 2.6706 | 1800 | 0.0006 | - |
212
- | 2.7448 | 1850 | 0.0005 | - |
213
- | 2.8190 | 1900 | 0.0005 | - |
214
- | 2.8932 | 1950 | 0.0003 | - |
215
- | 2.9674 | 2000 | 0.0001 | - |
216
- | 3.0 | 2022 | - | 0.0367 |
217
 
218
  * The bold row denotes the saved checkpoint.
219
  ### Framework Versions
 
152
 
153
  ### Training Hyperparameters
154
  - batch_size: (8, 8)
155
+ - num_epochs: (2, 2)
156
  - max_steps: -1
157
  - sampling_strategy: oversampling
158
  - body_learning_rate: (2e-05, 1e-05)
 
171
  | Epoch | Step | Training Loss | Validation Loss |
172
  |:-------:|:-------:|:-------------:|:---------------:|
173
  | 0.0015 | 1 | 0.306 | - |
174
+ | 0.0742 | 50 | 0.253 | - |
175
+ | 0.1484 | 100 | 0.2533 | - |
176
+ | 0.2226 | 150 | 0.0709 | - |
177
+ | 0.2967 | 200 | 0.0403 | - |
178
+ | 0.3709 | 250 | 0.0523 | - |
179
+ | 0.4451 | 300 | 0.0064 | - |
180
+ | 0.5193 | 350 | 0.0206 | - |
181
+ | 0.5935 | 400 | 0.0032 | - |
182
+ | 0.6677 | 450 | 0.0027 | - |
183
+ | 0.7418 | 500 | 0.002 | - |
184
+ | 0.8160 | 550 | 0.0015 | - |
185
+ | 0.8902 | 600 | 0.0018 | - |
186
+ | 0.9644 | 650 | 0.001 | - |
187
+ | **1.0** | **674** | **-** | **0.0358** |
188
+ | 1.0386 | 700 | 0.0005 | - |
189
+ | 1.1128 | 750 | 0.0011 | - |
190
+ | 1.1869 | 800 | 0.0004 | - |
191
+ | 1.2611 | 850 | 0.0016 | - |
192
+ | 1.3353 | 900 | 0.0009 | - |
193
+ | 1.4095 | 950 | 0.0019 | - |
194
+ | 1.4837 | 1000 | 0.0006 | - |
195
+ | 1.5579 | 1050 | 0.0003 | - |
196
+ | 1.6320 | 1100 | 0.0003 | - |
197
+ | 1.7062 | 1150 | 0.0009 | - |
198
+ | 1.7804 | 1200 | 0.0002 | - |
199
+ | 1.8546 | 1250 | 0.0003 | - |
200
+ | 1.9288 | 1300 | 0.0016 | - |
201
+ | 2.0 | 1348 | - | 0.038 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
202
 
203
  * The bold row denotes the saved checkpoint.
204
  ### Framework Versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bebe5f397c57f2ca489e733f61c25c367c05a1ebb9a879f4179434cc013d28e
3
  size 473211752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5586eddf36424ae42a7996a1878032bb1bb1170f551a88c98eb5278dd66943f
3
  size 473211752
model_head.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96f55b45d940a45bdc44ae7a4b37c9ca75137f0e1ee8ccaa2bcc4c48be8c335a
3
  size 68591
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c084f347819474456f1d3d42b5fae24e7e8d0725d7c99505fe755ecc28ebe144
3
  size 68591