Hugging Face's logo

marcelomoreno26
/
all-mpnet-base-v2-absa-polarity

Text Classification
setfit
Safetensors
sentence-transformers
mpnet
absa
generated_from_setfit_trainer
Eval Results
Model card Files Community
marcelomoreno26 commited on
Commit
f9e357c
•
1 Parent(s): ab138d5

Add SetFit ABSA model

Browse files
Files changed (13) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +553 -0
  3. config.json +24 -0
  4. config_sentence_transformers.json +9 -0
  5. config_setfit.json +10 -0
  6. model.safetensors +3 -0
  7. model_head.pkl +3 -0
  8. modules.json +20 -0
  9. sentence_bert_config.json +4 -0
  10. special_tokens_map.json +51 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +72 -0
  13. vocab.txt +0 -0
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 +1,553 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: setfit
3
+ tags:
4
+ - setfit
5
+ - absa
6
+ - sentence-transformers
7
+ - text-classification
8
+ - generated_from_setfit_trainer
9
+ base_model: sentence-transformers/all-mpnet-base-v2
10
+ metrics:
11
+ - accuracy
12
+ widget:
13
+ - text: Needs Power and Mouse Cable to Plug in:Needs Power and Mouse Cable to Plug
14
+ in back instead of side, In the way of operating a mouse in small area.
15
+ - text: wireless router via built-in wireless took no time:Connecting to my wireless
16
+ router via built-in wireless took no time at all.
17
+ - text: The battery life is probably an:The battery life is probably an hour at best.
18
+ - text: and with free shipping and no tax:The 13" Macbook Pro just fits in my budget
19
+ and with free shipping and no tax to CA this is the best price we can get for
20
+ a great product.
21
+ - text: product is top quality.:The price was very good, and the product is top quality.
22
+ pipeline_tag: text-classification
23
+ inference: false
24
+ model-index:
25
+ - name: SetFit Polarity Model with sentence-transformers/all-mpnet-base-v2
26
+ results:
27
+ - task:
28
+ type: text-classification
29
+ name: Text Classification
30
+ dataset:
31
+ name: Unknown
32
+ type: unknown
33
+ split: test
34
+ metrics:
35
+ - type: accuracy
36
+ value: 0.7788235294117647
37
+ name: Accuracy
38
+ ---
39
+
40
+ # SetFit Polarity Model with sentence-transformers/all-mpnet-base-v2
41
+
42
+ This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Aspect Based Sentiment Analysis (ABSA). This SetFit model uses [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-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. In particular, this model is in charge of classifying aspect polarities.
43
+
44
+ The model has been trained using an efficient few-shot learning technique that involves:
45
+
46
+ 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
47
+ 2. Training a classification head with features from the fine-tuned Sentence Transformer.
48
+
49
+ This model was trained within the context of a larger system for ABSA, which looks like so:
50
+
51
+ 1. Use a spaCy model to select possible aspect span candidates.
52
+ 2. Use a SetFit model to filter these possible aspect span candidates.
53
+ 3. **Use this SetFit model to classify the filtered aspect span candidates.**
54
+
55
+ ## Model Details
56
+
57
+ ### Model Description
58
+ - **Model Type:** SetFit
59
+ - **Sentence Transformer body:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2)
60
+ - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
61
+ - **spaCy Model:** en_core_web_sm
62
+ - **SetFitABSA Aspect Model:** [setfit-absa-aspect](https://huggingface.co/setfit-absa-aspect)
63
+ - **SetFitABSA Polarity Model:** [marcelomoreno26/all-mpnet-base-v2-absa-polarity2](https://huggingface.co/marcelomoreno26/all-mpnet-base-v2-absa-polarity2)
64
+ - **Maximum Sequence Length:** 384 tokens
65
+ - **Number of Classes:** 4 classes
66
+ <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
67
+ <!-- - **Language:** Unknown -->
68
+ <!-- - **License:** Unknown -->
69
+
70
+ ### Model Sources
71
+
72
+ - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
73
+ - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
74
+ - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
75
+
76
+ ### Model Labels
77
+ | Label | Examples |
78
+ |:---------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
79
+ | neutral | <ul><li>'skip taking the cord with me because:I charge it at night and skip taking the cord with me because of the good battery life.'</li><li>'The tech guy then said the:The tech guy then said the service center does not do 1-to-1 exchange and I have to direct my concern to the "sales" team, which is the retail shop which I bought my netbook from.'</li><li>'all dark, power light steady, hard:\xa0One night I turned the freaking thing off after using it, the next day I turn it on, no GUI, screen all dark, power light steady, hard drive light steady and not flashing as it usually does.'</li></ul> |
80
+ | positive | <ul><li>'of the good battery life.:I charge it at night and skip taking the cord with me because of the good battery life.'</li><li>'is of high quality, has a:it is of high quality, has a killer GUI, is extremely stable, is highly expandable, is bundled with lots of very good applications, is easy to use, and is absolutely gorgeous.'</li><li>'has a killer GUI, is extremely:it is of high quality, has a killer GUI, is extremely stable, is highly expandable, is bundled with lots of very good applications, is easy to use, and is absolutely gorgeous.'</li></ul> |
81
+ | negative | <ul><li>'then said the service center does not do:The tech guy then said the service center does not do 1-to-1 exchange and I have to direct my concern to the "sales" team, which is the retail shop which I bought my netbook from.'</li><li>'concern to the "sales" team, which is:The tech guy then said the service center does not do 1-to-1 exchange and I have to direct my concern to the "sales" team, which is the retail shop which I bought my netbook from.'</li><li>'on, no GUI, screen all:\xa0One night I turned the freaking thing off after using it, the next day I turn it on, no GUI, screen all dark, power light steady, hard drive light steady and not flashing as it usually does.'</li></ul> |
82
+ | conflict | <ul><li>'-No backlit keyboard, but not:-No backlit keyboard, but not an issue for me.'</li><li>"to replace the battery once, but:I did have to replace the battery once, but that was only a couple months ago and it's been working perfect ever since."</li><li>'Yes, they cost more, but:Yes, they cost more, but they more than make up for it in speed, construction quality, and longevity.'</li></ul> |
83
+
84
+ ## Evaluation
85
+
86
+ ### Metrics
87
+ | Label | Accuracy |
88
+ |:--------|:---------|
89
+ | **all** | 0.7788 |
90
+
91
+ ## Uses
92
+
93
+ ### Direct Use for Inference
94
+
95
+ First install the SetFit library:
96
+
97
+ ```bash
98
+ pip install setfit
99
+ ```
100
+
101
+ Then you can load this model and run inference.
102
+
103
+ ```python
104
+ from setfit import AbsaModel
105
+
106
+ # Download from the 🤗 Hub
107
+ model = AbsaModel.from_pretrained(
108
+ "setfit-absa-aspect",
109
+ "marcelomoreno26/all-mpnet-base-v2-absa-polarity2",
110
+ )
111
+ # Run inference
112
+ preds = model("The food was great, but the venue is just way too busy.")
113
+ ```
114
+
115
+ <!--
116
+ ### Downstream Use
117
+
118
+ *List how someone could finetune this model on their own dataset.*
119
+ -->
120
+
121
+ <!--
122
+ ### Out-of-Scope Use
123
+
124
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
125
+ -->
126
+
127
+ <!--
128
+ ## Bias, Risks and Limitations
129
+
130
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
131
+ -->
132
+
133
+ <!--
134
+ ### Recommendations
135
+
136
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
137
+ -->
138
+
139
+ ## Training Details
140
+
141
+ ### Training Set Metrics
142
+ | Training set | Min | Median | Max |
143
+ |:-------------|:----|:--------|:----|
144
+ | Word count | 3 | 24.3447 | 80 |
145
+
146
+ | Label | Training Sample Count |
147
+ |:---------|:----------------------|
148
+ | negative | 235 |
149
+ | neutral | 127 |
150
+ | positive | 271 |
151
+
152
+ ### Training Hyperparameters
153
+ - batch_size: (16, 2)
154
+ - num_epochs: (1, 16)
155
+ - max_steps: -1
156
+ - sampling_strategy: oversampling
157
+ - body_learning_rate: (2e-05, 1e-05)
158
+ - head_learning_rate: 0.01
159
+ - loss: CosineSimilarityLoss
160
+ - distance_metric: cosine_distance
161
+ - margin: 0.25
162
+ - end_to_end: False
163
+ - use_amp: False
164
+ - warmup_proportion: 0.1
165
+ - seed: 42
166
+ - eval_max_steps: -1
167
+ - load_best_model_at_end: False
168
+
169
+ ### Training Results
170
+ | Epoch | Step | Training Loss | Validation Loss |
171
+ |:------:|:-----:|:-------------:|:---------------:|
172
+ | 0.3333 | 1 | 0.3749 | - |
173
+ | 0.0030 | 50 | 0.3097 | - |
174
+ | 0.0059 | 100 | 0.2214 | - |
175
+ | 0.0089 | 150 | 0.2125 | - |
176
+ | 0.0119 | 200 | 0.3202 | - |
177
+ | 0.0148 | 250 | 0.1878 | - |
178
+ | 0.0178 | 300 | 0.1208 | - |
179
+ | 0.0208 | 350 | 0.2414 | - |
180
+ | 0.0237 | 400 | 0.1961 | - |
181
+ | 0.0267 | 450 | 0.0607 | - |
182
+ | 0.0296 | 500 | 0.1103 | - |
183
+ | 0.0326 | 550 | 0.1213 | - |
184
+ | 0.0356 | 600 | 0.0972 | - |
185
+ | 0.0385 | 650 | 0.0124 | - |
186
+ | 0.0415 | 700 | 0.0151 | - |
187
+ | 0.0445 | 750 | 0.1517 | - |
188
+ | 0.0474 | 800 | 0.004 | - |
189
+ | 0.0504 | 850 | 0.0204 | - |
190
+ | 0.0534 | 900 | 0.0541 | - |
191
+ | 0.0563 | 950 | 0.003 | - |
192
+ | 0.0593 | 1000 | 0.0008 | - |
193
+ | 0.0623 | 1050 | 0.0703 | - |
194
+ | 0.0652 | 1100 | 0.0013 | - |
195
+ | 0.0682 | 1150 | 0.0007 | - |
196
+ | 0.0712 | 1200 | 0.0009 | - |
197
+ | 0.0741 | 1250 | 0.0004 | - |
198
+ | 0.0771 | 1300 | 0.0004 | - |
199
+ | 0.0801 | 1350 | 0.0005 | - |
200
+ | 0.0830 | 1400 | 0.0006 | - |
201
+ | 0.0860 | 1450 | 0.0004 | - |
202
+ | 0.0889 | 1500 | 0.0002 | - |
203
+ | 0.0919 | 1550 | 0.0002 | - |
204
+ | 0.0949 | 1600 | 0.0001 | - |
205
+ | 0.0978 | 1650 | 0.0006 | - |
206
+ | 0.1008 | 1700 | 0.0002 | - |
207
+ | 0.1038 | 1750 | 0.0012 | - |
208
+ | 0.1067 | 1800 | 0.0008 | - |
209
+ | 0.1097 | 1850 | 0.0048 | - |
210
+ | 0.1127 | 1900 | 0.0007 | - |
211
+ | 0.1156 | 1950 | 0.0001 | - |
212
+ | 0.1186 | 2000 | 0.0001 | - |
213
+ | 0.1216 | 2050 | 0.0001 | - |
214
+ | 0.1245 | 2100 | 0.0001 | - |
215
+ | 0.1275 | 2150 | 0.0001 | - |
216
+ | 0.1305 | 2200 | 0.0001 | - |
217
+ | 0.1334 | 2250 | 0.0 | - |
218
+ | 0.1364 | 2300 | 0.0001 | - |
219
+ | 0.1394 | 2350 | 0.0002 | - |
220
+ | 0.1423 | 2400 | 0.0 | - |
221
+ | 0.1453 | 2450 | 0.0 | - |
222
+ | 0.1482 | 2500 | 0.0589 | - |
223
+ | 0.1512 | 2550 | 0.0036 | - |
224
+ | 0.1542 | 2600 | 0.0013 | - |
225
+ | 0.1571 | 2650 | 0.0 | - |
226
+ | 0.1601 | 2700 | 0.0001 | - |
227
+ | 0.1631 | 2750 | 0.0004 | - |
228
+ | 0.1660 | 2800 | 0.0 | - |
229
+ | 0.1690 | 2850 | 0.0002 | - |
230
+ | 0.1720 | 2900 | 0.0096 | - |
231
+ | 0.1749 | 2950 | 0.0 | - |
232
+ | 0.1779 | 3000 | 0.0 | - |
233
+ | 0.1809 | 3050 | 0.0001 | - |
234
+ | 0.1838 | 3100 | 0.0 | - |
235
+ | 0.1868 | 3150 | 0.0001 | - |
236
+ | 0.1898 | 3200 | 0.0001 | - |
237
+ | 0.1927 | 3250 | 0.0 | - |
238
+ | 0.1957 | 3300 | 0.0 | - |
239
+ | 0.1986 | 3350 | 0.0001 | - |
240
+ | 0.2016 | 3400 | 0.0 | - |
241
+ | 0.2046 | 3450 | 0.0002 | - |
242
+ | 0.2075 | 3500 | 0.0 | - |
243
+ | 0.2105 | 3550 | 0.0 | - |
244
+ | 0.2135 | 3600 | 0.0001 | - |
245
+ | 0.2164 | 3650 | 0.0 | - |
246
+ | 0.2194 | 3700 | 0.0 | - |
247
+ | 0.2224 | 3750 | 0.0001 | - |
248
+ | 0.2253 | 3800 | 0.0 | - |
249
+ | 0.2283 | 3850 | 0.0 | - |
250
+ | 0.2313 | 3900 | 0.0 | - |
251
+ | 0.2342 | 3950 | 0.0 | - |
252
+ | 0.2372 | 4000 | 0.0 | - |
253
+ | 0.2402 | 4050 | 0.0 | - |
254
+ | 0.2431 | 4100 | 0.0 | - |
255
+ | 0.2461 | 4150 | 0.0 | - |
256
+ | 0.2491 | 4200 | 0.0 | - |
257
+ | 0.2520 | 4250 | 0.0 | - |
258
+ | 0.2550 | 4300 | 0.0 | - |
259
+ | 0.2579 | 4350 | 0.0 | - |
260
+ | 0.2609 | 4400 | 0.0 | - |
261
+ | 0.2639 | 4450 | 0.0 | - |
262
+ | 0.2668 | 4500 | 0.0 | - |
263
+ | 0.2698 | 4550 | 0.0 | - |
264
+ | 0.2728 | 4600 | 0.0 | - |
265
+ | 0.2757 | 4650 | 0.0 | - |
266
+ | 0.2787 | 4700 | 0.0 | - |
267
+ | 0.2817 | 4750 | 0.0 | - |
268
+ | 0.2846 | 4800 | 0.0 | - |
269
+ | 0.2876 | 4850 | 0.0001 | - |
270
+ | 0.2906 | 4900 | 0.0071 | - |
271
+ | 0.2935 | 4950 | 0.1151 | - |
272
+ | 0.2965 | 5000 | 0.0055 | - |
273
+ | 0.2995 | 5050 | 0.0005 | - |
274
+ | 0.3024 | 5100 | 0.0041 | - |
275
+ | 0.3054 | 5150 | 0.0001 | - |
276
+ | 0.3083 | 5200 | 0.0003 | - |
277
+ | 0.3113 | 5250 | 0.0001 | - |
278
+ | 0.3143 | 5300 | 0.0 | - |
279
+ | 0.3172 | 5350 | 0.0001 | - |
280
+ | 0.3202 | 5400 | 0.0 | - |
281
+ | 0.3232 | 5450 | 0.0 | - |
282
+ | 0.3261 | 5500 | 0.0 | - |
283
+ | 0.3291 | 5550 | 0.0 | - |
284
+ | 0.3321 | 5600 | 0.0 | - |
285
+ | 0.3350 | 5650 | 0.0 | - |
286
+ | 0.3380 | 5700 | 0.0 | - |
287
+ | 0.3410 | 5750 | 0.0 | - |
288
+ | 0.3439 | 5800 | 0.0 | - |
289
+ | 0.3469 | 5850 | 0.0 | - |
290
+ | 0.3499 | 5900 | 0.0 | - |
291
+ | 0.3528 | 5950 | 0.0 | - |
292
+ | 0.3558 | 6000 | 0.0 | - |
293
+ | 0.3588 | 6050 | 0.0 | - |
294
+ | 0.3617 | 6100 | 0.0 | - |
295
+ | 0.3647 | 6150 | 0.0 | - |
296
+ | 0.3676 | 6200 | 0.0 | - |
297
+ | 0.3706 | 6250 | 0.0 | - |
298
+ | 0.3736 | 6300 | 0.0 | - |
299
+ | 0.3765 | 6350 | 0.0 | - |
300
+ | 0.3795 | 6400 | 0.0 | - |
301
+ | 0.3825 | 6450 | 0.0 | - |
302
+ | 0.3854 | 6500 | 0.0 | - |
303
+ | 0.3884 | 6550 | 0.0 | - |
304
+ | 0.3914 | 6600 | 0.0 | - |
305
+ | 0.3943 | 6650 | 0.0 | - |
306
+ | 0.3973 | 6700 | 0.0 | - |
307
+ | 0.4003 | 6750 | 0.0 | - |
308
+ | 0.4032 | 6800 | 0.0 | - |
309
+ | 0.4062 | 6850 | 0.0 | - |
310
+ | 0.4092 | 6900 | 0.0 | - |
311
+ | 0.4121 | 6950 | 0.0 | - |
312
+ | 0.4151 | 7000 | 0.0 | - |
313
+ | 0.4181 | 7050 | 0.0 | - |
314
+ | 0.4210 | 7100 | 0.0 | - |
315
+ | 0.4240 | 7150 | 0.0 | - |
316
+ | 0.4269 | 7200 | 0.0 | - |
317
+ | 0.4299 | 7250 | 0.0 | - |
318
+ | 0.4329 | 7300 | 0.0 | - |
319
+ | 0.4358 | 7350 | 0.0 | - |
320
+ | 0.4388 | 7400 | 0.0 | - |
321
+ | 0.4418 | 7450 | 0.0 | - |
322
+ | 0.4447 | 7500 | 0.0 | - |
323
+ | 0.4477 | 7550 | 0.0 | - |
324
+ | 0.4507 | 7600 | 0.0 | - |
325
+ | 0.4536 | 7650 | 0.0003 | - |
326
+ | 0.4566 | 7700 | 0.0 | - |
327
+ | 0.4596 | 7750 | 0.0 | - |
328
+ | 0.4625 | 7800 | 0.0 | - |
329
+ | 0.4655 | 7850 | 0.0 | - |
330
+ | 0.4685 | 7900 | 0.0 | - |
331
+ | 0.4714 | 7950 | 0.0 | - |
332
+ | 0.4744 | 8000 | 0.0 | - |
333
+ | 0.4773 | 8050 | 0.0 | - |
334
+ | 0.4803 | 8100 | 0.0 | - |
335
+ | 0.4833 | 8150 | 0.0 | - |
336
+ | 0.4862 | 8200 | 0.0 | - |
337
+ | 0.4892 | 8250 | 0.0 | - |
338
+ | 0.4922 | 8300 | 0.0 | - |
339
+ | 0.4951 | 8350 | 0.0 | - |
340
+ | 0.4981 | 8400 | 0.0 | - |
341
+ | 0.5011 | 8450 | 0.0 | - |
342
+ | 0.5040 | 8500 | 0.0 | - |
343
+ | 0.5070 | 8550 | 0.0 | - |
344
+ | 0.5100 | 8600 | 0.0 | - |
345
+ | 0.5129 | 8650 | 0.0 | - |
346
+ | 0.5159 | 8700 | 0.0 | - |
347
+ | 0.5189 | 8750 | 0.0 | - |
348
+ | 0.5218 | 8800 | 0.0 | - |
349
+ | 0.5248 | 8850 | 0.0 | - |
350
+ | 0.5278 | 8900 | 0.0 | - |
351
+ | 0.5307 | 8950 | 0.0 | - |
352
+ | 0.5337 | 9000 | 0.0 | - |
353
+ | 0.5366 | 9050 | 0.0 | - |
354
+ | 0.5396 | 9100 | 0.0 | - |
355
+ | 0.5426 | 9150 | 0.0 | - |
356
+ | 0.5455 | 9200 | 0.0 | - |
357
+ | 0.5485 | 9250 | 0.0 | - |
358
+ | 0.5515 | 9300 | 0.0 | - |
359
+ | 0.5544 | 9350 | 0.0 | - |
360
+ | 0.5574 | 9400 | 0.0 | - |
361
+ | 0.5604 | 9450 | 0.0 | - |
362
+ | 0.5633 | 9500 | 0.0 | - |
363
+ | 0.5663 | 9550 | 0.0 | - |
364
+ | 0.5693 | 9600 | 0.0 | - |
365
+ | 0.5722 | 9650 | 0.0 | - |
366
+ | 0.5752 | 9700 | 0.0 | - |
367
+ | 0.5782 | 9750 | 0.0 | - |
368
+ | 0.5811 | 9800 | 0.0 | - |
369
+ | 0.5841 | 9850 | 0.0 | - |
370
+ | 0.5870 | 9900 | 0.0 | - |
371
+ | 0.5900 | 9950 | 0.0 | - |
372
+ | 0.5930 | 10000 | 0.0 | - |
373
+ | 0.5959 | 10050 | 0.0 | - |
374
+ | 0.5989 | 10100 | 0.0 | - |
375
+ | 0.6019 | 10150 | 0.0 | - |
376
+ | 0.6048 | 10200 | 0.0 | - |
377
+ | 0.6078 | 10250 | 0.0 | - |
378
+ | 0.6108 | 10300 | 0.0 | - |
379
+ | 0.6137 | 10350 | 0.0 | - |
380
+ | 0.6167 | 10400 | 0.0 | - |
381
+ | 0.6197 | 10450 | 0.0 | - |
382
+ | 0.6226 | 10500 | 0.0 | - |
383
+ | 0.6256 | 10550 | 0.0 | - |
384
+ | 0.6286 | 10600 | 0.0 | - |
385
+ | 0.6315 | 10650 | 0.0 | - |
386
+ | 0.6345 | 10700 | 0.0 | - |
387
+ | 0.6375 | 10750 | 0.0 | - |
388
+ | 0.6404 | 10800 | 0.0 | - |
389
+ | 0.6434 | 10850 | 0.0 | - |
390
+ | 0.6463 | 10900 | 0.0 | - |
391
+ | 0.6493 | 10950 | 0.0 | - |
392
+ | 0.6523 | 11000 | 0.0 | - |
393
+ | 0.6552 | 11050 | 0.0 | - |
394
+ | 0.6582 | 11100 | 0.0 | - |
395
+ | 0.6612 | 11150 | 0.0 | - |
396
+ | 0.6641 | 11200 | 0.0 | - |
397
+ | 0.6671 | 11250 | 0.0 | - |
398
+ | 0.6701 | 11300 | 0.0 | - |
399
+ | 0.6730 | 11350 | 0.0 | - |
400
+ | 0.6760 | 11400 | 0.0 | - |
401
+ | 0.6790 | 11450 | 0.0 | - |
402
+ | 0.6819 | 11500 | 0.0 | - |
403
+ | 0.6849 | 11550 | 0.0 | - |
404
+ | 0.6879 | 11600 | 0.0 | - |
405
+ | 0.6908 | 11650 | 0.0 | - |
406
+ | 0.6938 | 11700 | 0.0 | - |
407
+ | 0.6968 | 11750 | 0.0 | - |
408
+ | 0.6997 | 11800 | 0.0 | - |
409
+ | 0.7027 | 11850 | 0.0 | - |
410
+ | 0.7056 | 11900 | 0.0 | - |
411
+ | 0.7086 | 11950 | 0.0 | - |
412
+ | 0.7116 | 12000 | 0.0 | - |
413
+ | 0.7145 | 12050 | 0.0 | - |
414
+ | 0.7175 | 12100 | 0.0 | - |
415
+ | 0.7205 | 12150 | 0.0 | - |
416
+ | 0.7234 | 12200 | 0.0 | - |
417
+ | 0.7264 | 12250 | 0.0 | - |
418
+ | 0.7294 | 12300 | 0.0 | - |
419
+ | 0.7323 | 12350 | 0.0 | - |
420
+ | 0.7353 | 12400 | 0.0 | - |
421
+ | 0.7383 | 12450 | 0.0 | - |
422
+ | 0.7412 | 12500 | 0.0 | - |
423
+ | 0.7442 | 12550 | 0.0 | - |
424
+ | 0.7472 | 12600 | 0.0 | - |
425
+ | 0.7501 | 12650 | 0.0 | - |
426
+ | 0.7531 | 12700 | 0.0 | - |
427
+ | 0.7560 | 12750 | 0.0 | - |
428
+ | 0.7590 | 12800 | 0.0 | - |
429
+ | 0.7620 | 12850 | 0.0 | - |
430
+ | 0.7649 | 12900 | 0.0 | - |
431
+ | 0.7679 | 12950 | 0.0 | - |
432
+ | 0.7709 | 13000 | 0.0 | - |
433
+ | 0.7738 | 13050 | 0.0 | - |
434
+ | 0.7768 | 13100 | 0.0 | - |
435
+ | 0.7798 | 13150 | 0.0 | - |
436
+ | 0.7827 | 13200 | 0.0 | - |
437
+ | 0.7857 | 13250 | 0.0 | - |
438
+ | 0.7887 | 13300 | 0.0 | - |
439
+ | 0.7916 | 13350 | 0.0 | - |
440
+ | 0.7946 | 13400 | 0.0 | - |
441
+ | 0.7976 | 13450 | 0.0 | - |
442
+ | 0.8005 | 13500 | 0.0 | - |
443
+ | 0.8035 | 13550 | 0.0 | - |
444
+ | 0.8065 | 13600 | 0.0 | - |
445
+ | 0.8094 | 13650 | 0.0 | - |
446
+ | 0.8124 | 13700 | 0.0 | - |
447
+ | 0.8153 | 13750 | 0.0 | - |
448
+ | 0.8183 | 13800 | 0.0 | - |
449
+ | 0.8213 | 13850 | 0.0 | - |
450
+ | 0.8242 | 13900 | 0.0 | - |
451
+ | 0.8272 | 13950 | 0.0 | - |
452
+ | 0.8302 | 14000 | 0.0 | - |
453
+ | 0.8331 | 14050 | 0.0 | - |
454
+ | 0.8361 | 14100 | 0.0 | - |
455
+ | 0.8391 | 14150 | 0.0 | - |
456
+ | 0.8420 | 14200 | 0.0 | - |
457
+ | 0.8450 | 14250 | 0.0 | - |
458
+ | 0.8480 | 14300 | 0.0 | - |
459
+ | 0.8509 | 14350 | 0.0 | - |
460
+ | 0.8539 | 14400 | 0.0 | - |
461
+ | 0.8569 | 14450 | 0.0 | - |
462
+ | 0.8598 | 14500 | 0.0 | - |
463
+ | 0.8628 | 14550 | 0.0 | - |
464
+ | 0.8657 | 14600 | 0.0 | - |
465
+ | 0.8687 | 14650 | 0.0 | - |
466
+ | 0.8717 | 14700 | 0.0 | - |
467
+ | 0.8746 | 14750 | 0.0 | - |
468
+ | 0.8776 | 14800 | 0.0 | - |
469
+ | 0.8806 | 14850 | 0.0 | - |
470
+ | 0.8835 | 14900 | 0.0 | - |
471
+ | 0.8865 | 14950 | 0.0 | - |
472
+ | 0.8895 | 15000 | 0.0 | - |
473
+ | 0.8924 | 15050 | 0.0 | - |
474
+ | 0.8954 | 15100 | 0.0 | - |
475
+ | 0.8984 | 15150 | 0.0 | - |
476
+ | 0.9013 | 15200 | 0.0 | - |
477
+ | 0.9043 | 15250 | 0.0 | - |
478
+ | 0.9073 | 15300 | 0.0 | - |
479
+ | 0.9102 | 15350 | 0.0 | - |
480
+ | 0.9132 | 15400 | 0.0 | - |
481
+ | 0.9162 | 15450 | 0.0 | - |
482
+ | 0.9191 | 15500 | 0.0 | - |
483
+ | 0.9221 | 15550 | 0.0 | - |
484
+ | 0.9250 | 15600 | 0.0 | - |
485
+ | 0.9280 | 15650 | 0.0 | - |
486
+ | 0.9310 | 15700 | 0.0 | - |
487
+ | 0.9339 | 15750 | 0.0 | - |
488
+ | 0.9369 | 15800 | 0.0 | - |
489
+ | 0.9399 | 15850 | 0.0 | - |
490
+ | 0.9428 | 15900 | 0.0 | - |
491
+ | 0.9458 | 15950 | 0.0 | - |
492
+ | 0.9488 | 16000 | 0.0 | - |
493
+ | 0.9517 | 16050 | 0.0 | - |
494
+ | 0.9547 | 16100 | 0.0 | - |
495
+ | 0.9577 | 16150 | 0.0 | - |
496
+ | 0.9606 | 16200 | 0.0 | - |
497
+ | 0.9636 | 16250 | 0.0 | - |
498
+ | 0.9666 | 16300 | 0.0 | - |
499
+ | 0.9695 | 16350 | 0.0 | - |
500
+ | 0.9725 | 16400 | 0.0 | - |
501
+ | 0.9755 | 16450 | 0.0 | - |
502
+ | 0.9784 | 16500 | 0.0 | - |
503
+ | 0.9814 | 16550 | 0.0 | - |
504
+ | 0.9843 | 16600 | 0.0 | - |
505
+ | 0.9873 | 16650 | 0.0 | - |
506
+ | 0.9903 | 16700 | 0.0 | - |
507
+ | 0.9932 | 16750 | 0.0 | - |
508
+ | 0.9962 | 16800 | 0.0 | - |
509
+ | 0.9992 | 16850 | 0.0 | - |
510
+
511
+ ### Framework Versions
512
+ - Python: 3.10.12
513
+ - SetFit: 1.0.3
514
+ - Sentence Transformers: 2.7.0
515
+ - spaCy: 3.7.4
516
+ - Transformers: 4.40.1
517
+ - PyTorch: 2.2.1+cu121
518
+ - Datasets: 2.19.0
519
+ - Tokenizers: 0.19.1
520
+
521
+ ## Citation
522
+
523
+ ### BibTeX
524
+ ```bibtex
525
+ @article{https://doi.org/10.48550/arxiv.2209.11055,
526
+ doi = {10.48550/ARXIV.2209.11055},
527
+ url = {https://arxiv.org/abs/2209.11055},
528
+ author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
529
+ keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
530
+ title = {Efficient Few-Shot Learning Without Prompts},
531
+ publisher = {arXiv},
532
+ year = {2022},
533
+ copyright = {Creative Commons Attribution 4.0 International}
534
+ }
535
+ ```
536
+
537
+ <!--
538
+ ## Glossary
539
+
540
+ *Clearly define terms in order to be accessible across audiences.*
541
+ -->
542
+
543
+ <!--
544
+ ## Model Card Authors
545
+
546
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
547
+ -->
548
+
549
+ <!--
550
+ ## Model Card Contact
551
+
552
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
553
+ -->
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/all-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": "4.40.1",
23
+ "vocab_size": 30527
24
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.0.0",
4
+ "transformers": "4.6.1",
5
+ "pytorch": "1.8.1"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null
9
+ }
config_setfit.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "spacy_model": "en_core_web_sm",
3
+ "span_context": 3,
4
+ "labels": [
5
+ "negative",
6
+ "neutral",
7
+ "positive"
8
+ ],
9
+ "normalize_embeddings": false
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a911235a0bf27fb25af20dd532fc3a551dac8177eac73abe411bbbc85ca0bfd
3
+ size 437967672
model_head.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:486376c4f67873eedbaf34ad89caa44f09c5f238a67f3948ed14a42c78ab237c
3
+ size 25559
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 384,
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 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "104": {
36
+ "content": "[UNK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "30526": {
44
+ "content": "<mask>",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "bos_token": "<s>",
53
+ "clean_up_tokenization_spaces": true,
54
+ "cls_token": "<s>",
55
+ "do_lower_case": true,
56
+ "eos_token": "</s>",
57
+ "mask_token": "<mask>",
58
+ "max_length": 128,
59
+ "model_max_length": 512,
60
+ "pad_to_multiple_of": null,
61
+ "pad_token": "<pad>",
62
+ "pad_token_type_id": 0,
63
+ "padding_side": "right",
64
+ "sep_token": "</s>",
65
+ "stride": 0,
66
+ "strip_accents": null,
67
+ "tokenize_chinese_chars": true,
68
+ "tokenizer_class": "MPNetTokenizer",
69
+ "truncation_side": "right",
70
+ "truncation_strategy": "longest_first",
71
+ "unk_token": "[UNK]"
72
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff