Hugging Face's logo

Netta1994
/
setfit_baai_cybereason_gpt-4o_improved-cot-instructions_chat_few_shot_generated_remov

Text Classification
setfit
Safetensors
sentence-transformers
bert
generated_from_setfit_trainer
Eval Results
Model card Files Community
Netta1994 commited on
Commit
0f3fc4a
•
1 Parent(s): c091d77

Add SetFit model

Browse files
Files changed (4) hide show
  1. README.md +64 -32
  2. config_setfit.json +2 -2
  3. model.safetensors +1 -1
  4. model_head.pkl +1 -1
README.md CHANGED
@@ -180,7 +180,7 @@ Evaluation:")
180
 
181
  ### Training Hyperparameters
182
  - batch_size: (16, 16)
183
- - num_epochs: (1, 1)
184
  - max_steps: -1
185
  - sampling_strategy: oversampling
186
  - num_iterations: 20
@@ -201,37 +201,69 @@ Evaluation:")
201
  | Epoch | Step | Training Loss | Validation Loss |
202
  |:------:|:----:|:-------------:|:---------------:|
203
  | 0.0006 | 1 | 0.2154 | - |
204
- | 0.0316 | 50 | 0.2575 | - |
205
- | 0.0632 | 100 | 0.2525 | - |
206
- | 0.0948 | 150 | 0.2567 | - |
207
- | 0.1263 | 200 | 0.2345 | - |
208
- | 0.1579 | 250 | 0.1831 | - |
209
- | 0.1895 | 300 | 0.1548 | - |
210
- | 0.2211 | 350 | 0.1225 | - |
211
- | 0.2527 | 400 | 0.0948 | - |
212
- | 0.2843 | 450 | 0.0578 | - |
213
- | 0.3159 | 500 | 0.0309 | - |
214
- | 0.3474 | 550 | 0.0241 | - |
215
- | 0.3790 | 600 | 0.0212 | - |
216
- | 0.4106 | 650 | 0.016 | - |
217
- | 0.4422 | 700 | 0.007 | - |
218
- | 0.4738 | 750 | 0.0037 | - |
219
- | 0.5054 | 800 | 0.0045 | - |
220
- | 0.5370 | 850 | 0.0046 | - |
221
- | 0.5685 | 900 | 0.0047 | - |
222
- | 0.6001 | 950 | 0.0028 | - |
223
- | 0.6317 | 1000 | 0.0042 | - |
224
- | 0.6633 | 1050 | 0.0024 | - |
225
- | 0.6949 | 1100 | 0.0023 | - |
226
- | 0.7265 | 1150 | 0.002 | - |
227
- | 0.7581 | 1200 | 0.0023 | - |
228
- | 0.7896 | 1250 | 0.0025 | - |
229
- | 0.8212 | 1300 | 0.0022 | - |
230
- | 0.8528 | 1350 | 0.0017 | - |
231
- | 0.8844 | 1400 | 0.0019 | - |
232
- | 0.9160 | 1450 | 0.0021 | - |
233
- | 0.9476 | 1500 | 0.0019 | - |
234
- | 0.9792 | 1550 | 0.0015 | - |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
235
 
236
  ### Framework Versions
237
  - Python: 3.10.14
 
180
 
181
  ### Training Hyperparameters
182
  - batch_size: (16, 16)
183
+ - num_epochs: (2, 2)
184
  - max_steps: -1
185
  - sampling_strategy: oversampling
186
  - num_iterations: 20
 
201
  | Epoch | Step | Training Loss | Validation Loss |
202
  |:------:|:----:|:-------------:|:---------------:|
203
  | 0.0006 | 1 | 0.2154 | - |
204
+ | 0.0316 | 50 | 0.2582 | - |
205
+ | 0.0632 | 100 | 0.2517 | - |
206
+ | 0.0948 | 150 | 0.2562 | - |
207
+ | 0.1263 | 200 | 0.2532 | - |
208
+ | 0.1579 | 250 | 0.2412 | - |
209
+ | 0.1895 | 300 | 0.184 | - |
210
+ | 0.2211 | 350 | 0.1608 | - |
211
+ | 0.2527 | 400 | 0.1487 | - |
212
+ | 0.2843 | 450 | 0.117 | - |
213
+ | 0.3159 | 500 | 0.0685 | - |
214
+ | 0.3474 | 550 | 0.0327 | - |
215
+ | 0.3790 | 600 | 0.0257 | - |
216
+ | 0.4106 | 650 | 0.0139 | - |
217
+ | 0.4422 | 700 | 0.012 | - |
218
+ | 0.4738 | 750 | 0.0047 | - |
219
+ | 0.5054 | 800 | 0.0046 | - |
220
+ | 0.5370 | 850 | 0.0042 | - |
221
+ | 0.5685 | 900 | 0.0058 | - |
222
+ | 0.6001 | 950 | 0.0029 | - |
223
+ | 0.6317 | 1000 | 0.0055 | - |
224
+ | 0.6633 | 1050 | 0.0033 | - |
225
+ | 0.6949 | 1100 | 0.0026 | - |
226
+ | 0.7265 | 1150 | 0.0026 | - |
227
+ | 0.7581 | 1200 | 0.0033 | - |
228
+ | 0.7896 | 1250 | 0.0049 | - |
229
+ | 0.8212 | 1300 | 0.0043 | - |
230
+ | 0.8528 | 1350 | 0.0019 | - |
231
+ | 0.8844 | 1400 | 0.0015 | - |
232
+ | 0.9160 | 1450 | 0.0014 | - |
233
+ | 0.9476 | 1500 | 0.0017 | - |
234
+ | 0.9792 | 1550 | 0.0013 | - |
235
+ | 1.0107 | 1600 | 0.0019 | - |
236
+ | 1.0423 | 1650 | 0.0012 | - |
237
+ | 1.0739 | 1700 | 0.0011 | - |
238
+ | 1.1055 | 1750 | 0.0013 | - |
239
+ | 1.1371 | 1800 | 0.0012 | - |
240
+ | 1.1687 | 1850 | 0.0013 | - |
241
+ | 1.2003 | 1900 | 0.0013 | - |
242
+ | 1.2318 | 1950 | 0.0012 | - |
243
+ | 1.2634 | 2000 | 0.0011 | - |
244
+ | 1.2950 | 2050 | 0.0012 | - |
245
+ | 1.3266 | 2100 | 0.0011 | - |
246
+ | 1.3582 | 2150 | 0.0011 | - |
247
+ | 1.3898 | 2200 | 0.0012 | - |
248
+ | 1.4214 | 2250 | 0.0014 | - |
249
+ | 1.4529 | 2300 | 0.0011 | - |
250
+ | 1.4845 | 2350 | 0.001 | - |
251
+ | 1.5161 | 2400 | 0.0011 | - |
252
+ | 1.5477 | 2450 | 0.001 | - |
253
+ | 1.5793 | 2500 | 0.001 | - |
254
+ | 1.6109 | 2550 | 0.0012 | - |
255
+ | 1.6425 | 2600 | 0.0011 | - |
256
+ | 1.6740 | 2650 | 0.0011 | - |
257
+ | 1.7056 | 2700 | 0.001 | - |
258
+ | 1.7372 | 2750 | 0.001 | - |
259
+ | 1.7688 | 2800 | 0.001 | - |
260
+ | 1.8004 | 2850 | 0.001 | - |
261
+ | 1.8320 | 2900 | 0.001 | - |
262
+ | 1.8636 | 2950 | 0.001 | - |
263
+ | 1.8951 | 3000 | 0.001 | - |
264
+ | 1.9267 | 3050 | 0.0009 | - |
265
+ | 1.9583 | 3100 | 0.0011 | - |
266
+ | 1.9899 | 3150 | 0.001 | - |
267
 
268
  ### Framework Versions
269
  - Python: 3.10.14
config_setfit.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "normalize_embeddings": false,
3
- "labels": null
4
  }
 
1
  {
2
+ "labels": null,
3
+ "normalize_embeddings": false
4
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c88a2d0771f6b42018f7cc279e4f87dc060bcb68b7aa2159b2236ff8185e10be
3
  size 437951328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0563c6c88be189a85180f766e9ed949e58b181bc171fb37d086dc09ab1f6f629
3
  size 437951328
model_head.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4eece35c86b02908ccffc7842a0741dc062d28939a95eb495e6830237af6f4f9
3
  size 7007
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0cbd7f4d7fc2252a1b7a5c30c76e0b8802e27a962b75f13d6422a6f11846a00
3
  size 7007