kaustubhgap commited on
Commit
993d0ac
1 Parent(s): 29b03ca

Push model using huggingface_hub.

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,475 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: sentence-transformers/paraphrase-mpnet-base-v2
3
+ library_name: setfit
4
+ metrics:
5
+ - accuracy
6
+ pipeline_tag: text-classification
7
+ tags:
8
+ - setfit
9
+ - sentence-transformers
10
+ - text-classification
11
+ - generated_from_setfit_trainer
12
+ widget:
13
+ - text: one piece
14
+ - text: tube
15
+ - text: heavy weight
16
+ - text: track
17
+ - text: unitard
18
+ inference: true
19
+ model-index:
20
+ - name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2
21
+ results:
22
+ - task:
23
+ type: text-classification
24
+ name: Text Classification
25
+ dataset:
26
+ name: Unknown
27
+ type: unknown
28
+ split: test
29
+ metrics:
30
+ - type: accuracy
31
+ value: 0.5493273542600897
32
+ name: Accuracy
33
+ ---
34
+
35
+ # SetFit with sentence-transformers/paraphrase-mpnet-base-v2
36
+
37
+ This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
38
+
39
+ The model has been trained using an efficient few-shot learning technique that involves:
40
+
41
+ 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
42
+ 2. Training a classification head with features from the fine-tuned Sentence Transformer.
43
+
44
+ ## Model Details
45
+
46
+ ### Model Description
47
+ - **Model Type:** SetFit
48
+ - **Sentence Transformer body:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2)
49
+ - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
50
+ - **Maximum Sequence Length:** 512 tokens
51
+ - **Number of Classes:** 119 classes
52
+ <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
53
+ <!-- - **Language:** Unknown -->
54
+ <!-- - **License:** Unknown -->
55
+
56
+ ### Model Sources
57
+
58
+ - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
59
+ - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
60
+ - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
61
+
62
+ ### Model Labels
63
+ | Label | Examples |
64
+ |:------|:---------------------------------------------------------------------------------------------------|
65
+ | 79 | <ul><li>'peony middle notes'</li><li>'lemon middle notes'</li><li>'coconut middle notes'</li></ul> |
66
+ | 86 | <ul><li>'no print/no pattern'</li><li>'two tone'</li><li>'diagonal stripe'</li></ul> |
67
+ | 37 | <ul><li>'eel skin leather'</li><li>'metal'</li><li>'raffia'</li></ul> |
68
+ | 82 | <ul><li>'collarless'</li><li>'peaked lapel'</li><li>'front keyhole'</li></ul> |
69
+ | 95 | <ul><li>'standard toe'</li><li>'wide toe'</li><li>'extra wide toe'</li></ul> |
70
+ | 83 | <ul><li>'indoor'</li><li>'hike'</li><li>'beach'</li></ul> |
71
+ | 107 | <ul><li>'surplice'</li><li>'messenger bag'</li><li>'camera bag'</li></ul> |
72
+ | 19 | <ul><li>'mary jane'</li><li>'zip around wallet'</li><li>'tongue buckle'</li></ul> |
73
+ | 102 | <ul><li>'slits at knee'</li><li>'slits above hips'</li><li>'front slit at hem'</li></ul> |
74
+ | 35 | <ul><li>'tie'</li><li>'gem embellishment'</li><li>'caged'</li></ul> |
75
+ | 18 | <ul><li>'rolo chain'</li><li>'cord bracelet'</li><li>'figaro'</li></ul> |
76
+ | 65 | <ul><li>'wheat protein'</li><li>'rosemary ingredient'</li><li>'pea protein'</li></ul> |
77
+ | 68 | <ul><li>'bath towel'</li><li>'art print'</li><li>'reusable bottle'</li></ul> |
78
+ | 40 | <ul><li>'polyfill'</li><li>'silk fill'</li><li>'feather fill'</li></ul> |
79
+ | 50 | <ul><li>'palm grip'</li><li>'carpenter hook'</li><li>'storm flap'</li></ul> |
80
+ | 113 | <ul><li>'wide waistband'</li><li>'elastic inset'</li><li>'belt loops'</li></ul> |
81
+ | 75 | <ul><li>'glass'</li><li>'acrylic'</li><li>'opal'</li></ul> |
82
+ | 11 | <ul><li>'foam cups'</li><li>'wire'</li><li>'molded cups'</li></ul> |
83
+ | 38 | <ul><li>'dual layer fabric'</li><li>'2 way stretch'</li><li>'4 way stretch'</li></ul> |
84
+ | 63 | <ul><li>'light support'</li><li>'medium supprt'</li><li>'high support'</li></ul> |
85
+ | 44 | <ul><li>'face'</li><li>'hand'</li><li>'neck/dècolletage'</li></ul> |
86
+ | 115 | <ul><li>'soy wax'</li><li>'paraffin wax'</li></ul> |
87
+ | 42 | <ul><li>'regular'</li><li>'tailored'</li><li>'fitted'</li></ul> |
88
+ | 97 | <ul><li>'king'</li><li>'euro'</li><li>'standard'</li></ul> |
89
+ | 70 | <ul><li>'wrist length'</li><li>'above thigh'</li><li>'below bust'</li></ul> |
90
+ | 34 | <ul><li>'feminine'</li><li>'religious'</li><li>'boho'</li></ul> |
91
+ | 10 | <ul><li>'slim'</li><li>'regular'</li></ul> |
92
+ | 15 | <ul><li>'6-10 oz'</li><li>'11-20 oz'</li></ul> |
93
+ | 77 | <ul><li>'rose gold metal'</li><li>'gold plated'</li><li>'alloy'</li></ul> |
94
+ | 43 | <ul><li>'contrast inner lining'</li><li>'simple seaming'</li><li>'princess seams'</li></ul> |
95
+ | 7 | <ul><li>'neroli base notes'</li><li>'amber base notes'</li><li>'musk base notes'</li></ul> |
96
+ | 17 | <ul><li>'spot clean'</li><li>'dry clean'</li><li>'microwave safe'</li></ul> |
97
+ | 8 | <ul><li>'nourishing'</li><li>'firming'</li><li>'soothing/healing'</li></ul> |
98
+ | 103 | <ul><li>'lugged soles'</li><li>'non marking soles'</li></ul> |
99
+ | 26 | <ul><li>'wall control'</li><li>'switch control'</li></ul> |
100
+ | 99 | <ul><li>'fitted sleeves'</li><li>'fitted sleeve'</li><li>'structured sleeves'</li></ul> |
101
+ | 33 | <ul><li>'rim'</li><li>'feet'</li><li>'5 panel construction'</li></ul> |
102
+ | 64 | <ul><li>'mineral oil free'</li><li>'propylene glycol free'</li><li>'paraffin free'</li></ul> |
103
+ | 96 | <ul><li>'double strap'</li><li>'spaghetti straps'</li><li>'thin straps'</li></ul> |
104
+ | 1 | <ul><li>'shoulder back'</li><li>'full coverage'</li><li>'low back'</li></ul> |
105
+ | 62 | <ul><li>'rustic'</li><li>'coastal'</li><li>'scandinavian'</li></ul> |
106
+ | 39 | <ul><li>'metallic'</li><li>'swiss dot'</li><li>'base layer'</li></ul> |
107
+ | 60 | <ul><li>'halloween'</li><li>'christmas holiday'</li></ul> |
108
+ | 92 | <ul><li>'seamless'</li><li>'mid rise waist seam'</li><li>'flat seam'</li></ul> |
109
+ | 114 | <ul><li>'ultra high rise'</li><li>'mid rise'</li><li>'high waisted'</li></ul> |
110
+ | 105 | <ul><li>'top handle'</li><li>'detachable straps'</li><li>'chain strap'</li></ul> |
111
+ | 90 | <ul><li>'floral'</li><li>'psychedelic print'</li><li>'paisley'</li></ul> |
112
+ | 91 | <ul><li>'night'</li><li>'day'</li></ul> |
113
+ | 45 | <ul><li>'serum formulation'</li><li>'cream/creme'</li><li>'solid'</li></ul> |
114
+ | 59 | <ul><li>'strong hold'</li><li>'flexible hold'</li></ul> |
115
+ | 46 | <ul><li>'leather'</li><li>'fresh aquatic'</li><li>'green aromatic'</li></ul> |
116
+ | 21 | <ul><li>'matte'</li><li>'metallic'</li><li>'olive'</li></ul> |
117
+ | 69 | <ul><li>'cinnamon key notes'</li><li>'violet key notes'</li><li>'pepper key notes'</li></ul> |
118
+ | 101 | <ul><li>'dropped shoulder'</li><li>'puff shoulder'</li><li>'flutter sleeve'</li></ul> |
119
+ | 61 | <ul><li>'summer'</li><li>'everyday'</li><li>'indoor'</li></ul> |
120
+ | 104 | <ul><li>'wedding guest'</li><li>'bridal'</li><li>'halloween'</li></ul> |
121
+ | 32 | <ul><li>'indigo wash'</li><li>'acid wash'</li><li>'stonewash'</li></ul> |
122
+ | 51 | <ul><li>'still life graphic'</li><li>'sports graphic'</li><li>'star wars'</li></ul> |
123
+ | 48 | <ul><li>'beige'</li><li>'black'</li><li>'rose gold frame'</li></ul> |
124
+ | 87 | <ul><li>'medium pile'</li><li>'low pile'</li></ul> |
125
+ | 22 | <ul><li>'bright'</li><li>'pastel'</li><li>'light'</li></ul> |
126
+ | 41 | <ul><li>'matte finish'</li><li>'shiny finish'</li></ul> |
127
+ | 93 | <ul><li>'no buckle'</li><li>'geometric shape'</li><li>'straight silhouette'</li></ul> |
128
+ | 71 | <ul><li>'polarized'</li><li>'color tinted'</li><li>'mirrored'</li></ul> |
129
+ | 2 | <ul><li>'split back'</li><li>'racer back'</li><li>'open back'</li></ul> |
130
+ | 89 | <ul><li>'round stitch pocket'</li><li>'seam pocket'</li><li>'kangaroo pocket'</li></ul> |
131
+ | 20 | <ul><li>'removable hoodie'</li><li>'packable hood collar'</li><li>'hooded'</li></ul> |
132
+ | 52 | <ul><li>'thick'</li><li>'medium thick'</li></ul> |
133
+ | 55 | <ul><li>'amber head notes'</li><li>'lime head notes'</li><li>'musk head notes'</li></ul> |
134
+ | 58 | <ul><li>'back curved hem'</li><li>'twist hem'</li><li>'ribbed hem'</li></ul> |
135
+ | 118 | <ul><li>'light wood'</li><li>'medium wood'</li></ul> |
136
+ | 25 | <ul><li>'gifts for him'</li><li>'apres ski'</li><li>'cozy'</li></ul> |
137
+ | 109 | <ul><li>'closed toe'</li><li>'square toe'</li><li>'round toe'</li></ul> |
138
+ | 30 | <ul><li>'extended cuffs'</li><li>'storm cuffs'</li><li>'elastic cuff'</li></ul> |
139
+ | 24 | <ul><li>'ingrown hairs'</li><li>'frizz'</li><li>'redness'</li></ul> |
140
+ | 9 | <ul><li>'high cut'</li><li>'string bikini'</li></ul> |
141
+ | 94 | <ul><li>'opaque'</li><li>'sheer'</li></ul> |
142
+ | 16 | <ul><li>'2 card slot'</li><li>'card slots'</li></ul> |
143
+ | 78 | <ul><li>'gothcore'</li><li>'vanilla girl'</li><li>'dyed out'</li></ul> |
144
+ | 4 | <ul><li>'layered'</li><li>'bangle'</li><li>'cuff'</li></ul> |
145
+ | 23 | <ul><li>'parfum'</li><li>'eau de toilette'</li></ul> |
146
+ | 111 | <ul><li>'delicate'</li><li>'statement'</li></ul> |
147
+ | 12 | <ul><li>'flat brim'</li><li>'curved brim'</li><li>'fold over brim'</li></ul> |
148
+ | 98 | <ul><li>'dry'</li><li>'acne prone'</li><li>'mature'</li></ul> |
149
+ | 57 | <ul><li>'stacked heel'</li><li>'kitten heel'</li><li>'cone heel'</li></ul> |
150
+ | 67 | <ul><li>'id slot'</li><li>'interior pocket'</li><li>'interior zipper pocket'</li></ul> |
151
+ | 31 | <ul><li>'light wash'</li><li>'medium wash'</li><li>'colored'</li></ul> |
152
+ | 85 | <ul><li>'detailed stitching pant'</li><li>'simple seaming'</li></ul> |
153
+ | 116 | <ul><li>'knotted'</li><li>'percale'</li><li>'waffle weave'</li></ul> |
154
+ | 88 | <ul><li>'shag'</li><li>'cut pile'</li></ul> |
155
+ | 74 | <ul><li>'study hall'</li><li>'y2k'</li><li>'enchanted'</li></ul> |
156
+ | 72 | <ul><li>'fur'</li><li>'fleece'</li><li>'mesh'</li></ul> |
157
+ | 108 | <ul><li>'animal'</li><li>'love'</li></ul> |
158
+ | 73 | <ul><li>'unlined'</li><li>'fully lined'</li><li>'partially lined'</li></ul> |
159
+ | 13 | <ul><li>'wide brim'</li><li>'medium brim'</li></ul> |
160
+ | 76 | <ul><li>'bpa free material'</li><li>'scratch resistant material'</li></ul> |
161
+ | 54 | <ul><li>'straight handle'</li><li>'curved handle'</li></ul> |
162
+ | 100 | <ul><li>'rolled up sleeves'</li><li>'3/4 sleeve'</li><li>'bracelet length'</li></ul> |
163
+ | 84 | <ul><li>'manual open'</li><li>'auto open'</li></ul> |
164
+ | 14 | <ul><li>'wide'</li><li>'medium'</li></ul> |
165
+ | 27 | <ul><li>'superhero'</li><li>'disney'</li></ul> |
166
+ | 49 | <ul><li>'half rim'</li><li>'full rim'</li></ul> |
167
+ | 29 | <ul><li>'tall crown'</li><li>'short crown'</li></ul> |
168
+ | 106 | <ul><li>'low stretch'</li><li>'non stretch'</li></ul> |
169
+ | 112 | <ul><li>'mid vamp'</li><li>'high vamp'</li></ul> |
170
+ | 66 | <ul><li>'large interior'</li><li>'medium interior'</li><li>'small interior'</li></ul> |
171
+ | 53 | <ul><li>'all hair types'</li><li>'damaged/dry hair'</li></ul> |
172
+ | 117 | <ul><li>'light weight'</li><li>'mid weight'</li></ul> |
173
+ | 81 | <ul><li>'low cut'</li><li>'mid chest neckline'</li><li>'open front'</li></ul> |
174
+ | 5 | <ul><li>'thin band'</li><li>'soft band elastic'</li><li>'elastic band'</li></ul> |
175
+ | 28 | <ul><li>'flat top crown'</li><li>'round crown'</li><li>'no crown'</li></ul> |
176
+ | 56 | <ul><li>'ultra high heel'</li><li>'mid heel'</li><li>'high heel'</li></ul> |
177
+ | 110 | <ul><li>'relaxed'</li><li>'tailored'</li></ul> |
178
+ | 47 | <ul><li>'uplifting'</li><li>'bold'</li></ul> |
179
+ | 3 | <ul><li>'changing pad'</li><li>'bottle pocket'</li></ul> |
180
+ | 0 | <ul><li>'squeeze dispenser'</li><li>'dropper'</li></ul> |
181
+ | 80 | <ul><li>'wall mount'</li><li>'ceiling mount'</li></ul> |
182
+ | 6 | <ul><li>'medium'</li><li>'wide'</li></ul> |
183
+ | 36 | <ul><li>'exterior pocket'</li><li>'exterior snap pocket'</li></ul> |
184
+
185
+ ## Evaluation
186
+
187
+ ### Metrics
188
+ | Label | Accuracy |
189
+ |:--------|:---------|
190
+ | **all** | 0.5493 |
191
+
192
+ ## Uses
193
+
194
+ ### Direct Use for Inference
195
+
196
+ First install the SetFit library:
197
+
198
+ ```bash
199
+ pip install setfit
200
+ ```
201
+
202
+ Then you can load this model and run inference.
203
+
204
+ ```python
205
+ from setfit import SetFitModel
206
+
207
+ # Download from the 🤗 Hub
208
+ model = SetFitModel.from_pretrained("kaustubhgap/kaustubh_setfit_1iteration")
209
+ # Run inference
210
+ preds = model("tube")
211
+ ```
212
+
213
+ <!--
214
+ ### Downstream Use
215
+
216
+ *List how someone could finetune this model on their own dataset.*
217
+ -->
218
+
219
+ <!--
220
+ ### Out-of-Scope Use
221
+
222
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
223
+ -->
224
+
225
+ <!--
226
+ ## Bias, Risks and Limitations
227
+
228
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
229
+ -->
230
+
231
+ <!--
232
+ ### Recommendations
233
+
234
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
235
+ -->
236
+
237
+ ## Training Details
238
+
239
+ ### Training Set Metrics
240
+ | Training set | Min | Median | Max |
241
+ |:-------------|:----|:-------|:----|
242
+ | Word count | 1 | 1.7047 | 6 |
243
+
244
+ | Label | Training Sample Count |
245
+ |:------|:----------------------|
246
+ | 0 | 2 |
247
+ | 1 | 5 |
248
+ | 2 | 12 |
249
+ | 3 | 2 |
250
+ | 4 | 6 |
251
+ | 5 | 3 |
252
+ | 6 | 2 |
253
+ | 7 | 12 |
254
+ | 8 | 16 |
255
+ | 9 | 2 |
256
+ | 10 | 2 |
257
+ | 11 | 11 |
258
+ | 12 | 4 |
259
+ | 13 | 2 |
260
+ | 14 | 2 |
261
+ | 15 | 2 |
262
+ | 16 | 2 |
263
+ | 17 | 6 |
264
+ | 18 | 9 |
265
+ | 19 | 63 |
266
+ | 20 | 8 |
267
+ | 21 | 31 |
268
+ | 22 | 6 |
269
+ | 23 | 2 |
270
+ | 24 | 13 |
271
+ | 25 | 5 |
272
+ | 26 | 2 |
273
+ | 27 | 2 |
274
+ | 28 | 3 |
275
+ | 29 | 2 |
276
+ | 30 | 13 |
277
+ | 31 | 3 |
278
+ | 32 | 7 |
279
+ | 33 | 22 |
280
+ | 34 | 12 |
281
+ | 35 | 102 |
282
+ | 36 | 2 |
283
+ | 37 | 119 |
284
+ | 38 | 34 |
285
+ | 39 | 32 |
286
+ | 40 | 6 |
287
+ | 41 | 2 |
288
+ | 42 | 13 |
289
+ | 43 | 17 |
290
+ | 44 | 5 |
291
+ | 45 | 10 |
292
+ | 46 | 6 |
293
+ | 47 | 2 |
294
+ | 48 | 10 |
295
+ | 49 | 2 |
296
+ | 50 | 91 |
297
+ | 51 | 13 |
298
+ | 52 | 2 |
299
+ | 53 | 2 |
300
+ | 54 | 2 |
301
+ | 55 | 12 |
302
+ | 56 | 4 |
303
+ | 57 | 7 |
304
+ | 58 | 17 |
305
+ | 59 | 2 |
306
+ | 60 | 2 |
307
+ | 61 | 7 |
308
+ | 62 | 9 |
309
+ | 63 | 3 |
310
+ | 64 | 14 |
311
+ | 65 | 53 |
312
+ | 66 | 3 |
313
+ | 67 | 6 |
314
+ | 68 | 41 |
315
+ | 69 | 41 |
316
+ | 70 | 33 |
317
+ | 71 | 5 |
318
+ | 72 | 5 |
319
+ | 73 | 4 |
320
+ | 74 | 7 |
321
+ | 75 | 49 |
322
+ | 76 | 2 |
323
+ | 77 | 23 |
324
+ | 78 | 11 |
325
+ | 79 | 12 |
326
+ | 80 | 2 |
327
+ | 81 | 5 |
328
+ | 82 | 33 |
329
+ | 83 | 33 |
330
+ | 84 | 2 |
331
+ | 85 | 2 |
332
+ | 86 | 17 |
333
+ | 87 | 2 |
334
+ | 88 | 2 |
335
+ | 89 | 10 |
336
+ | 90 | 29 |
337
+ | 91 | 2 |
338
+ | 92 | 8 |
339
+ | 93 | 21 |
340
+ | 94 | 2 |
341
+ | 95 | 3 |
342
+ | 96 | 5 |
343
+ | 97 | 10 |
344
+ | 98 | 5 |
345
+ | 99 | 6 |
346
+ | 100 | 6 |
347
+ | 101 | 12 |
348
+ | 102 | 13 |
349
+ | 103 | 2 |
350
+ | 104 | 10 |
351
+ | 105 | 28 |
352
+ | 106 | 2 |
353
+ | 107 | 321 |
354
+ | 108 | 2 |
355
+ | 109 | 10 |
356
+ | 110 | 2 |
357
+ | 111 | 2 |
358
+ | 112 | 2 |
359
+ | 113 | 15 |
360
+ | 114 | 4 |
361
+ | 115 | 2 |
362
+ | 116 | 5 |
363
+ | 117 | 2 |
364
+ | 118 | 2 |
365
+
366
+ ### Training Hyperparameters
367
+ - batch_size: (16, 16)
368
+ - num_epochs: (1, 1)
369
+ - max_steps: -1
370
+ - sampling_strategy: oversampling
371
+ - num_iterations: 10
372
+ - body_learning_rate: (2e-05, 1e-05)
373
+ - head_learning_rate: 0.01
374
+ - loss: CosineSimilarityLoss
375
+ - distance_metric: cosine_distance
376
+ - margin: 0.25
377
+ - end_to_end: False
378
+ - use_amp: False
379
+ - warmup_proportion: 0.1
380
+ - seed: 42
381
+ - eval_max_steps: -1
382
+ - load_best_model_at_end: False
383
+
384
+ ### Training Results
385
+ | Epoch | Step | Training Loss | Validation Loss |
386
+ |:------:|:----:|:-------------:|:---------------:|
387
+ | 0.0004 | 1 | 0.2895 | - |
388
+ | 0.0225 | 50 | 0.2059 | - |
389
+ | 0.0449 | 100 | 0.1794 | - |
390
+ | 0.0674 | 150 | 0.1994 | - |
391
+ | 0.0898 | 200 | 0.2708 | - |
392
+ | 0.1123 | 250 | 0.1355 | - |
393
+ | 0.1347 | 300 | 0.0695 | - |
394
+ | 0.1572 | 350 | 0.117 | - |
395
+ | 0.1796 | 400 | 0.0601 | - |
396
+ | 0.2021 | 450 | 0.0873 | - |
397
+ | 0.2245 | 500 | 0.07 | - |
398
+ | 0.2470 | 550 | 0.0805 | - |
399
+ | 0.2694 | 600 | 0.0204 | - |
400
+ | 0.2919 | 650 | 0.1059 | - |
401
+ | 0.3143 | 700 | 0.1178 | - |
402
+ | 0.3368 | 750 | 0.1804 | - |
403
+ | 0.3592 | 800 | 0.0979 | - |
404
+ | 0.3817 | 850 | 0.1597 | - |
405
+ | 0.4041 | 900 | 0.1215 | - |
406
+ | 0.4266 | 950 | 0.0188 | - |
407
+ | 0.4490 | 1000 | 0.0738 | - |
408
+ | 0.4715 | 1050 | 0.0635 | - |
409
+ | 0.4939 | 1100 | 0.1439 | - |
410
+ | 0.5164 | 1150 | 0.0684 | - |
411
+ | 0.5388 | 1200 | 0.0732 | - |
412
+ | 0.5613 | 1250 | 0.0401 | - |
413
+ | 0.5837 | 1300 | 0.1223 | - |
414
+ | 0.6062 | 1350 | 0.1044 | - |
415
+ | 0.6286 | 1400 | 0.0717 | - |
416
+ | 0.6511 | 1450 | 0.0413 | - |
417
+ | 0.6736 | 1500 | 0.0544 | - |
418
+ | 0.6960 | 1550 | 0.1419 | - |
419
+ | 0.7185 | 1600 | 0.0284 | - |
420
+ | 0.7409 | 1650 | 0.0484 | - |
421
+ | 0.7634 | 1700 | 0.0049 | - |
422
+ | 0.7858 | 1750 | 0.0229 | - |
423
+ | 0.8083 | 1800 | 0.0739 | - |
424
+ | 0.8307 | 1850 | 0.0371 | - |
425
+ | 0.8532 | 1900 | 0.0213 | - |
426
+ | 0.8756 | 1950 | 0.0753 | - |
427
+ | 0.8981 | 2000 | 0.0359 | - |
428
+ | 0.9205 | 2050 | 0.0232 | - |
429
+ | 0.9430 | 2100 | 0.0507 | - |
430
+ | 0.9654 | 2150 | 0.0258 | - |
431
+ | 0.9879 | 2200 | 0.0606 | - |
432
+ | 1.0 | 2227 | - | 0.2105 |
433
+
434
+ ### Framework Versions
435
+ - Python: 3.10.12
436
+ - SetFit: 1.0.3
437
+ - Sentence Transformers: 3.0.1
438
+ - Transformers: 4.36.1
439
+ - PyTorch: 2.0.1+cu118
440
+ - Datasets: 2.20.0
441
+ - Tokenizers: 0.15.0
442
+
443
+ ## Citation
444
+
445
+ ### BibTeX
446
+ ```bibtex
447
+ @article{https://doi.org/10.48550/arxiv.2209.11055,
448
+ doi = {10.48550/ARXIV.2209.11055},
449
+ url = {https://arxiv.org/abs/2209.11055},
450
+ author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
451
+ keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
452
+ title = {Efficient Few-Shot Learning Without Prompts},
453
+ publisher = {arXiv},
454
+ year = {2022},
455
+ copyright = {Creative Commons Attribution 4.0 International}
456
+ }
457
+ ```
458
+
459
+ <!--
460
+ ## Glossary
461
+
462
+ *Clearly define terms in order to be accessible across audiences.*
463
+ -->
464
+
465
+ <!--
466
+ ## Model Card Authors
467
+
468
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
469
+ -->
470
+
471
+ <!--
472
+ ## Model Card Contact
473
+
474
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
475
+ -->
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/paraphrase-mpnet-base-v2",
3
+ "architectures": [
4
+ "MPNetModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "mpnet",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "relative_attention_num_buckets": 32,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.36.1",
23
+ "vocab_size": 30527
24
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.0.1",
4
+ "transformers": "4.36.1",
5
+ "pytorch": "2.0.1+cu118"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": null
10
+ }
config_setfit.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "normalize_embeddings": false,
3
+ "labels": null
4
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35e7613963f82d98ed2072e93c29d2a955df8e41886a889b72fbb21eccc44814
3
+ size 437967672
model_head.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5660d91ba7f83f473e68fb50c0828330ebd1a4b249b3a571198d363411323a67
3
+ size 733923
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "104": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "30526": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "do_basic_tokenize": true,
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
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff