Hugging Face's logo

Chernoffface
/
fs-setfit-multilable-model

Text Classification
setfit
Safetensors
sentence-transformers
bert
generated_from_setfit_trainer
Model card Files Community
Chernoffface commited on
Commit
aa4e288
·
verified ·
1 Parent(s): b1c7463

Add SetFit model

Browse files
Files changed (4) hide show
  1. README.md +125 -12
  2. config_setfit.json +2 -2
  3. model.safetensors +1 -1
  4. model_head.pkl +2 -2
README.md CHANGED
@@ -9,15 +9,35 @@ base_model: sentence-transformers/paraphrase-mpnet-base-v2
9
  metrics:
10
  - accuracy
11
  widget:
12
- - text: The seminar offers a well-balanced mix of theory and case studies with a focus
13
- on mitigation and adaptation within the context of climate change and economics.
14
- - text: 'Juni Fachsprachliche Lehrwerke: Anspruche und Realitat 01.'
15
- - text: Grundlagen der Fachdidaktik Padagogik
16
- - text: Probleme losen lernen
17
- - text: Im Rahmen dieses Praxisseminars sollen Studierende einen fundierten Einblick
18
- in Ablaufe der Fragebogenkonstruktion, Datenerhebung und Datenanalyse erhalten.
 
 
 
 
 
 
19
  pipeline_tag: text-classification
20
  inference: false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  ---
22
 
23
  # SetFit with sentence-transformers/paraphrase-mpnet-base-v2
@@ -47,6 +67,13 @@ The model has been trained using an efficient few-shot learning technique that i
47
  - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
48
  - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
49
 
 
 
 
 
 
 
 
50
  ## Uses
51
 
52
  ### Direct Use for Inference
@@ -65,7 +92,7 @@ from setfit import SetFitModel
65
  # Download from the 🤗 Hub
66
  model = SetFitModel.from_pretrained("Chernoffface/fs-setfit-multilable-model")
67
  # Run inference
68
- preds = model("Probleme losen lernen")
69
  ```
70
 
71
  <!--
@@ -97,7 +124,7 @@ preds = model("Probleme losen lernen")
97
  ### Training Set Metrics
98
  | Training set | Min | Median | Max |
99
  |:-------------|:----|:--------|:----|
100
- | Word count | 2 | 18.2917 | 74 |
101
 
102
  ### Training Hyperparameters
103
  - batch_size: (16, 16)
@@ -121,9 +148,95 @@ preds = model("Probleme losen lernen")
121
  ### Training Results
122
  | Epoch | Step | Training Loss | Validation Loss |
123
  |:------:|:----:|:-------------:|:---------------:|
124
- | 0.0083 | 1 | 0.1978 | - |
125
- | 0.4167 | 50 | 0.1134 | - |
126
- | 0.8333 | 100 | 0.0439 | - |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
127
 
128
  ### Framework Versions
129
  - Python: 3.12.3
 
9
  metrics:
10
  - accuracy
11
  widget:
12
+ - text: In diesem Seminar an unserer Hochschule erhalten Sie eine umfassende Einführung
13
+ in die SCRUM-Methode und ihre Anwendung im agilen Arbeiten.
14
+ - text: 'Dazu untersuchen wir grundlegende Programmierkonzepte: wozu sie dienen und
15
+ wie sie funtionieren.'
16
+ - text: 'Modeling plays a very important role in reconstructing (as far as possible)
17
+ the complete and complex picture of the surroundings water systems and offers
18
+ a unique way to predict behavior of such multifaceted systems.
19
+
20
+
21
+ '
22
+ - text: Build an IT-based artifact using recent IoT, robotics, and applied AI technologies.
23
+ - text: Sie bietet eine Plattform, um neuartige auf Blockchain Technologie basierende
24
+ Anwendungen auf ihre Umsetzbarkeit und Sinnhaftigkeit zu überprüfen.
25
  pipeline_tag: text-classification
26
  inference: false
27
+ model-index:
28
+ - name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2
29
+ results:
30
+ - task:
31
+ type: text-classification
32
+ name: Text Classification
33
+ dataset:
34
+ name: Unknown
35
+ type: unknown
36
+ split: test
37
+ metrics:
38
+ - type: accuracy
39
+ value: 0.5225165562913907
40
+ name: Accuracy
41
  ---
42
 
43
  # SetFit with sentence-transformers/paraphrase-mpnet-base-v2
 
67
  - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
68
  - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
69
 
70
+ ## Evaluation
71
+
72
+ ### Metrics
73
+ | Label | Accuracy |
74
+ |:--------|:---------|
75
+ | **all** | 0.5225 |
76
+
77
  ## Uses
78
 
79
  ### Direct Use for Inference
 
92
  # Download from the 🤗 Hub
93
  model = SetFitModel.from_pretrained("Chernoffface/fs-setfit-multilable-model")
94
  # Run inference
95
+ preds = model("Build an IT-based artifact using recent IoT, robotics, and applied AI technologies.")
96
  ```
97
 
98
  <!--
 
124
  ### Training Set Metrics
125
  | Training set | Min | Median | Max |
126
  |:-------------|:----|:--------|:----|
127
+ | Word count | 1 | 12.9119 | 131 |
128
 
129
  ### Training Hyperparameters
130
  - batch_size: (16, 16)
 
148
  ### Training Results
149
  | Epoch | Step | Training Loss | Validation Loss |
150
  |:------:|:----:|:-------------:|:---------------:|
151
+ | 0.0045 | 1 | 0.1871 | - |
152
+ | 0.2273 | 50 | 0.1771 | - |
153
+ | 0.4545 | 100 | 0.0978 | - |
154
+ | 0.6818 | 150 | 0.0675 | - |
155
+ | 0.9091 | 200 | 0.0479 | - |
156
+ | 0.0045 | 1 | 0.0274 | - |
157
+ | 0.2273 | 50 | 0.0426 | - |
158
+ | 0.4545 | 100 | 0.0346 | - |
159
+ | 0.6818 | 150 | 0.0375 | - |
160
+ | 0.9091 | 200 | 0.0322 | - |
161
+ | 0.0003 | 1 | 0.2265 | - |
162
+ | 0.0127 | 50 | 0.1776 | - |
163
+ | 0.0254 | 100 | 0.1138 | - |
164
+ | 0.0380 | 150 | 0.0816 | - |
165
+ | 0.0507 | 200 | 0.055 | - |
166
+ | 0.0634 | 250 | 0.04 | - |
167
+ | 0.0761 | 300 | 0.031 | - |
168
+ | 0.0888 | 350 | 0.0227 | - |
169
+ | 0.1014 | 400 | 0.0222 | - |
170
+ | 0.1141 | 450 | 0.0206 | - |
171
+ | 0.1268 | 500 | 0.0191 | - |
172
+ | 0.1395 | 550 | 0.0239 | - |
173
+ | 0.1522 | 600 | 0.0181 | - |
174
+ | 0.1648 | 650 | 0.0263 | - |
175
+ | 0.1775 | 700 | 0.0175 | - |
176
+ | 0.1902 | 750 | 0.0157 | - |
177
+ | 0.2029 | 800 | 0.0178 | - |
178
+ | 0.2156 | 850 | 0.0189 | - |
179
+ | 0.2283 | 900 | 0.0121 | - |
180
+ | 0.2409 | 950 | 0.0203 | - |
181
+ | 0.2536 | 1000 | 0.0206 | - |
182
+ | 0.2663 | 1050 | 0.013 | - |
183
+ | 0.2790 | 1100 | 0.0167 | - |
184
+ | 0.2917 | 1150 | 0.0143 | - |
185
+ | 0.3043 | 1200 | 0.0151 | - |
186
+ | 0.3170 | 1250 | 0.0135 | - |
187
+ | 0.3297 | 1300 | 0.0109 | - |
188
+ | 0.3424 | 1350 | 0.011 | - |
189
+ | 0.3551 | 1400 | 0.0165 | - |
190
+ | 0.3677 | 1450 | 0.0133 | - |
191
+ | 0.3804 | 1500 | 0.0197 | - |
192
+ | 0.3931 | 1550 | 0.012 | - |
193
+ | 0.4058 | 1600 | 0.0137 | - |
194
+ | 0.4185 | 1650 | 0.0163 | - |
195
+ | 0.4311 | 1700 | 0.0089 | - |
196
+ | 0.4438 | 1750 | 0.0117 | - |
197
+ | 0.4565 | 1800 | 0.0139 | - |
198
+ | 0.4692 | 1850 | 0.01 | - |
199
+ | 0.4819 | 1900 | 0.0142 | - |
200
+ | 0.4945 | 1950 | 0.0094 | - |
201
+ | 0.5072 | 2000 | 0.0111 | - |
202
+ | 0.5199 | 2050 | 0.0119 | - |
203
+ | 0.5326 | 2100 | 0.0089 | - |
204
+ | 0.5453 | 2150 | 0.0087 | - |
205
+ | 0.5580 | 2200 | 0.007 | - |
206
+ | 0.5706 | 2250 | 0.0081 | - |
207
+ | 0.5833 | 2300 | 0.016 | - |
208
+ | 0.5960 | 2350 | 0.0105 | - |
209
+ | 0.6087 | 2400 | 0.0124 | - |
210
+ | 0.6214 | 2450 | 0.0059 | - |
211
+ | 0.6340 | 2500 | 0.01 | - |
212
+ | 0.6467 | 2550 | 0.0054 | - |
213
+ | 0.6594 | 2600 | 0.0059 | - |
214
+ | 0.6721 | 2650 | 0.0091 | - |
215
+ | 0.6848 | 2700 | 0.0133 | - |
216
+ | 0.6974 | 2750 | 0.0065 | - |
217
+ | 0.7101 | 2800 | 0.0081 | - |
218
+ | 0.7228 | 2850 | 0.0078 | - |
219
+ | 0.7355 | 2900 | 0.0079 | - |
220
+ | 0.7482 | 2950 | 0.01 | - |
221
+ | 0.7608 | 3000 | 0.0083 | - |
222
+ | 0.7735 | 3050 | 0.0114 | - |
223
+ | 0.7862 | 3100 | 0.0076 | - |
224
+ | 0.7989 | 3150 | 0.0083 | - |
225
+ | 0.8116 | 3200 | 0.0097 | - |
226
+ | 0.8242 | 3250 | 0.0077 | - |
227
+ | 0.8369 | 3300 | 0.0066 | - |
228
+ | 0.8496 | 3350 | 0.0113 | - |
229
+ | 0.8623 | 3400 | 0.0065 | - |
230
+ | 0.8750 | 3450 | 0.01 | - |
231
+ | 0.8876 | 3500 | 0.0098 | - |
232
+ | 0.9003 | 3550 | 0.0115 | - |
233
+ | 0.9130 | 3600 | 0.0073 | - |
234
+ | 0.9257 | 3650 | 0.0104 | - |
235
+ | 0.9384 | 3700 | 0.0059 | - |
236
+ | 0.9511 | 3750 | 0.006 | - |
237
+ | 0.9637 | 3800 | 0.0071 | - |
238
+ | 0.9764 | 3850 | 0.0061 | - |
239
+ | 0.9891 | 3900 | 0.0076 | - |
240
 
241
  ### Framework Versions
242
  - Python: 3.12.3
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 sha256:21e8d519f1b08e5864723f20364921b88296cd50a13b9009b1d2f4afd9574b85
3
  size 437967672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7c99ff204a58ae07d43f49a81b58fdc45448a80549b2fb953bd0c3ab4092dc3
3
  size 437967672
model_head.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95a2bad9927eda79596a3a3c5498183ac0efeb0f5105eae54b9594609d2ac75f
3
- size 39828
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c807fcf656d53d492516233e19fc7a9d21240e42f4d5cf6d4ec1d40ec25f2167
3
+ size 72196