Chernoffface commited on
Commit
2c2d6bc
·
verified ·
1 Parent(s): 0eb71c7

Add SetFit model

Browse files
Files changed (5) hide show
  1. README.md +95 -80
  2. config.json +1 -1
  3. model.safetensors +1 -1
  4. model_head.pkl +1 -1
  5. tokenizer_config.json +0 -7
README.md CHANGED
@@ -22,7 +22,7 @@ widget:
22
  - text: 'Wie entsteht überhaupt eine Ausstellung und in diesem Fall: eine, die weniger
23
  auf den Wert des Originals als die Kreativität ihrer Besucher setzt?'
24
  pipeline_tag: text-classification
25
- inference: true
26
  ---
27
 
28
  # SetFit with sentence-transformers/paraphrase-mpnet-base-v2
@@ -126,85 +126,100 @@ preds = model("Grundlagen der Fachdidaktik Pädagogik")
126
  ### Training Results
127
  | Epoch | Step | Training Loss | Validation Loss |
128
  |:------:|:----:|:-------------:|:---------------:|
129
- | 0.0003 | 1 | 0.4461 | - |
130
- | 0.0127 | 50 | 0.517 | - |
131
- | 0.0254 | 100 | 0.3178 | - |
132
- | 0.0380 | 150 | 0.0591 | - |
133
- | 0.0507 | 200 | 0.0278 | - |
134
- | 0.0634 | 250 | 0.0319 | - |
135
- | 0.0761 | 300 | 0.0175 | - |
136
- | 0.0888 | 350 | 0.0148 | - |
137
- | 0.1014 | 400 | 0.0181 | - |
138
- | 0.1141 | 450 | 0.0116 | - |
139
- | 0.1268 | 500 | 0.0297 | - |
140
- | 0.1395 | 550 | 0.0164 | - |
141
- | 0.1522 | 600 | 0.0152 | - |
142
- | 0.1648 | 650 | 0.0133 | - |
143
- | 0.1775 | 700 | 0.0156 | - |
144
- | 0.1902 | 750 | 0.0102 | - |
145
- | 0.2029 | 800 | 0.0096 | - |
146
- | 0.2156 | 850 | 0.0094 | - |
147
- | 0.2283 | 900 | 0.0077 | - |
148
- | 0.2409 | 950 | 0.0072 | - |
149
- | 0.2536 | 1000 | 0.006 | - |
150
- | 0.2663 | 1050 | 0.0098 | - |
151
- | 0.2790 | 1100 | 0.0108 | - |
152
- | 0.2917 | 1150 | 0.0078 | - |
153
- | 0.3043 | 1200 | 0.0089 | - |
154
- | 0.3170 | 1250 | 0.0059 | - |
155
- | 0.3297 | 1300 | 0.0067 | - |
156
- | 0.3424 | 1350 | 0.0136 | - |
157
- | 0.3551 | 1400 | 0.004 | - |
158
- | 0.3677 | 1450 | 0.0041 | - |
159
- | 0.3804 | 1500 | 0.0081 | - |
160
- | 0.3931 | 1550 | 0.0034 | - |
161
- | 0.4058 | 1600 | 0.0056 | - |
162
- | 0.4185 | 1650 | 0.0045 | - |
163
- | 0.4311 | 1700 | 0.0035 | - |
164
- | 0.4438 | 1750 | 0.0044 | - |
165
- | 0.4565 | 1800 | 0.0042 | - |
166
- | 0.4692 | 1850 | 0.0061 | - |
167
- | 0.4819 | 1900 | 0.0073 | - |
168
- | 0.4945 | 1950 | 0.0056 | - |
169
- | 0.5072 | 2000 | 0.0048 | - |
170
- | 0.5199 | 2050 | 0.0023 | - |
171
- | 0.5326 | 2100 | 0.0036 | - |
172
- | 0.5453 | 2150 | 0.0037 | - |
173
- | 0.5580 | 2200 | 0.0048 | - |
174
- | 0.5706 | 2250 | 0.0042 | - |
175
- | 0.5833 | 2300 | 0.0065 | - |
176
- | 0.5960 | 2350 | 0.0046 | - |
177
- | 0.6087 | 2400 | 0.0056 | - |
178
- | 0.6214 | 2450 | 0.0029 | - |
179
- | 0.6340 | 2500 | 0.004 | - |
180
- | 0.6467 | 2550 | 0.0019 | - |
181
- | 0.6594 | 2600 | 0.0022 | - |
182
- | 0.6721 | 2650 | 0.0021 | - |
183
- | 0.6848 | 2700 | 0.0036 | - |
184
- | 0.6974 | 2750 | 0.0013 | - |
185
- | 0.7101 | 2800 | 0.001 | - |
186
- | 0.7228 | 2850 | 0.004 | - |
187
- | 0.7355 | 2900 | 0.0025 | - |
188
- | 0.7482 | 2950 | 0.0012 | - |
189
- | 0.7608 | 3000 | 0.0011 | - |
190
- | 0.7735 | 3050 | 0.001 | - |
191
- | 0.7862 | 3100 | 0.0008 | - |
192
- | 0.7989 | 3150 | 0.0014 | - |
193
- | 0.8116 | 3200 | 0.0041 | - |
194
- | 0.8242 | 3250 | 0.0019 | - |
195
- | 0.8369 | 3300 | 0.0025 | - |
196
- | 0.8496 | 3350 | 0.0013 | - |
197
- | 0.8623 | 3400 | 0.0017 | - |
198
- | 0.8750 | 3450 | 0.0021 | - |
199
- | 0.8876 | 3500 | 0.0013 | - |
200
- | 0.9003 | 3550 | 0.0016 | - |
201
- | 0.9130 | 3600 | 0.0041 | - |
202
- | 0.9257 | 3650 | 0.0037 | - |
203
- | 0.9384 | 3700 | 0.0012 | - |
204
- | 0.9511 | 3750 | 0.0022 | - |
205
- | 0.9637 | 3800 | 0.003 | - |
206
- | 0.9764 | 3850 | 0.0026 | - |
207
- | 0.9891 | 3900 | 0.0027 | - |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
208
 
209
  ### Framework Versions
210
  - Python: 3.12.3
 
22
  - text: 'Wie entsteht überhaupt eine Ausstellung und in diesem Fall: eine, die weniger
23
  auf den Wert des Originals als die Kreativität ihrer Besucher setzt?'
24
  pipeline_tag: text-classification
25
+ inference: false
26
  ---
27
 
28
  # SetFit with sentence-transformers/paraphrase-mpnet-base-v2
 
126
  ### Training Results
127
  | Epoch | Step | Training Loss | Validation Loss |
128
  |:------:|:----:|:-------------:|:---------------:|
129
+ | 0.0003 | 1 | 0.2958 | - |
130
+ | 0.0127 | 50 | 0.2471 | - |
131
+ | 0.0254 | 100 | 0.1602 | - |
132
+ | 0.0380 | 150 | 0.0884 | - |
133
+ | 0.0507 | 200 | 0.056 | - |
134
+ | 0.0634 | 250 | 0.0465 | - |
135
+ | 0.0761 | 300 | 0.0431 | - |
136
+ | 0.0888 | 350 | 0.0285 | - |
137
+ | 0.1014 | 400 | 0.0224 | - |
138
+ | 0.1141 | 450 | 0.0281 | - |
139
+ | 0.1268 | 500 | 0.024 | - |
140
+ | 0.1395 | 550 | 0.0271 | - |
141
+ | 0.1522 | 600 | 0.0223 | - |
142
+ | 0.1648 | 650 | 0.0314 | - |
143
+ | 0.1775 | 700 | 0.0213 | - |
144
+ | 0.0003 | 1 | 0.0019 | - |
145
+ | 0.0127 | 50 | 0.0184 | - |
146
+ | 0.0254 | 100 | 0.0232 | - |
147
+ | 0.0380 | 150 | 0.0138 | - |
148
+ | 0.0507 | 200 | 0.0165 | - |
149
+ | 0.0634 | 250 | 0.0179 | - |
150
+ | 0.0761 | 300 | 0.0133 | - |
151
+ | 0.0888 | 350 | 0.0117 | - |
152
+ | 0.1014 | 400 | 0.0093 | - |
153
+ | 0.1141 | 450 | 0.0091 | - |
154
+ | 0.1268 | 500 | 0.0153 | - |
155
+ | 0.1395 | 550 | 0.0194 | - |
156
+ | 0.1522 | 600 | 0.0129 | - |
157
+ | 0.1648 | 650 | 0.0138 | - |
158
+ | 0.1775 | 700 | 0.0166 | - |
159
+ | 0.1902 | 750 | 0.0169 | - |
160
+ | 0.2029 | 800 | 0.0202 | - |
161
+ | 0.2156 | 850 | 0.0186 | - |
162
+ | 0.2283 | 900 | 0.0128 | - |
163
+ | 0.2409 | 950 | 0.0206 | - |
164
+ | 0.2536 | 1000 | 0.0201 | - |
165
+ | 0.2663 | 1050 | 0.0152 | - |
166
+ | 0.2790 | 1100 | 0.0178 | - |
167
+ | 0.2917 | 1150 | 0.0166 | - |
168
+ | 0.3043 | 1200 | 0.0139 | - |
169
+ | 0.3170 | 1250 | 0.0098 | - |
170
+ | 0.3297 | 1300 | 0.0092 | - |
171
+ | 0.3424 | 1350 | 0.0118 | - |
172
+ | 0.3551 | 1400 | 0.0173 | - |
173
+ | 0.3677 | 1450 | 0.0131 | - |
174
+ | 0.3804 | 1500 | 0.0151 | - |
175
+ | 0.3931 | 1550 | 0.0127 | - |
176
+ | 0.4058 | 1600 | 0.0142 | - |
177
+ | 0.4185 | 1650 | 0.0156 | - |
178
+ | 0.4311 | 1700 | 0.0068 | - |
179
+ | 0.4438 | 1750 | 0.0136 | - |
180
+ | 0.4565 | 1800 | 0.0124 | - |
181
+ | 0.4692 | 1850 | 0.0104 | - |
182
+ | 0.4819 | 1900 | 0.0159 | - |
183
+ | 0.4945 | 1950 | 0.0109 | - |
184
+ | 0.5072 | 2000 | 0.011 | - |
185
+ | 0.5199 | 2050 | 0.0123 | - |
186
+ | 0.5326 | 2100 | 0.0087 | - |
187
+ | 0.5453 | 2150 | 0.0081 | - |
188
+ | 0.5580 | 2200 | 0.0072 | - |
189
+ | 0.5706 | 2250 | 0.0099 | - |
190
+ | 0.5833 | 2300 | 0.0137 | - |
191
+ | 0.5960 | 2350 | 0.0094 | - |
192
+ | 0.6087 | 2400 | 0.0165 | - |
193
+ | 0.6214 | 2450 | 0.0066 | - |
194
+ | 0.6340 | 2500 | 0.0123 | - |
195
+ | 0.6467 | 2550 | 0.0087 | - |
196
+ | 0.6594 | 2600 | 0.0101 | - |
197
+ | 0.6721 | 2650 | 0.0099 | - |
198
+ | 0.6848 | 2700 | 0.0157 | - |
199
+ | 0.6974 | 2750 | 0.0066 | - |
200
+ | 0.7101 | 2800 | 0.0098 | - |
201
+ | 0.7228 | 2850 | 0.0102 | - |
202
+ | 0.7355 | 2900 | 0.0112 | - |
203
+ | 0.7482 | 2950 | 0.0137 | - |
204
+ | 0.7608 | 3000 | 0.0096 | - |
205
+ | 0.7735 | 3050 | 0.013 | - |
206
+ | 0.7862 | 3100 | 0.0116 | - |
207
+ | 0.7989 | 3150 | 0.0102 | - |
208
+ | 0.8116 | 3200 | 0.0115 | - |
209
+ | 0.8242 | 3250 | 0.0133 | - |
210
+ | 0.8369 | 3300 | 0.0065 | - |
211
+ | 0.8496 | 3350 | 0.0117 | - |
212
+ | 0.8623 | 3400 | 0.0078 | - |
213
+ | 0.8750 | 3450 | 0.0099 | - |
214
+ | 0.8876 | 3500 | 0.0095 | - |
215
+ | 0.9003 | 3550 | 0.0119 | - |
216
+ | 0.9130 | 3600 | 0.008 | - |
217
+ | 0.9257 | 3650 | 0.0107 | - |
218
+ | 0.9384 | 3700 | 0.0066 | - |
219
+ | 0.9511 | 3750 | 0.006 | - |
220
+ | 0.9637 | 3800 | 0.0081 | - |
221
+ | 0.9764 | 3850 | 0.0076 | - |
222
+ | 0.9891 | 3900 | 0.009 | - |
223
 
224
  ### Framework Versions
225
  - Python: 3.12.3
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "Chernoffface/fs-setfit-multilable-model",
3
  "architectures": [
4
  "MPNetModel"
5
  ],
 
1
  {
2
+ "_name_or_path": "sentence-transformers/paraphrase-mpnet-base-v2",
3
  "architectures": [
4
  "MPNetModel"
5
  ],
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65022b93fb8307ebd460706dcd805a1ab736861dbc14bf5141645e90c9bda438
3
  size 437967672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f338f26460ce0761f855f083d0bdf7e4e8c6b106226f0182145797104f1a337
3
  size 437967672
model_head.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:992c2c2037ed4adda2442fde733a224bcb67198bba0ccd7772b98bdf9a2d187f
3
  size 72196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f3e1e8cc0d29abd675621896fdc71e39f1c728b5ca22eeb010daf553964b406
3
  size 72196
tokenizer_config.json CHANGED
@@ -48,19 +48,12 @@
48
  "do_lower_case": true,
49
  "eos_token": "</s>",
50
  "mask_token": "<mask>",
51
- "max_length": 512,
52
  "model_max_length": 512,
53
  "never_split": null,
54
- "pad_to_multiple_of": null,
55
  "pad_token": "<pad>",
56
- "pad_token_type_id": 0,
57
- "padding_side": "right",
58
  "sep_token": "</s>",
59
- "stride": 0,
60
  "strip_accents": null,
61
  "tokenize_chinese_chars": true,
62
  "tokenizer_class": "MPNetTokenizer",
63
- "truncation_side": "right",
64
- "truncation_strategy": "longest_first",
65
  "unk_token": "[UNK]"
66
  }
 
48
  "do_lower_case": true,
49
  "eos_token": "</s>",
50
  "mask_token": "<mask>",
 
51
  "model_max_length": 512,
52
  "never_split": null,
 
53
  "pad_token": "<pad>",
 
 
54
  "sep_token": "</s>",
 
55
  "strip_accents": null,
56
  "tokenize_chinese_chars": true,
57
  "tokenizer_class": "MPNetTokenizer",
 
 
58
  "unk_token": "[UNK]"
59
  }