Hugging Face's logo

Fikaaw
/
en-setfit-absa-model-aspect

Text Classification
setfit
Safetensors
sentence-transformers
mpnet
absa
generated_from_setfit_trainer
Eval Results
Model card Files Community
Fikaaw commited on
Commit
bd09084
•
1 Parent(s): 242a0de

Upload 12 files

Browse files
Files changed (12) hide show
  1. README.md +555 -3
  2. config.json +24 -0
  3. config_sentence_transformers.json +9 -0
  4. config_setfit.json +9 -0
  5. model.safetensors +3 -0
  6. model_head.pkl +3 -0
  7. modules.json +14 -0
  8. sentence_bert_config.json +4 -0
  9. special_tokens_map.json +51 -0
  10. tokenizer.json +0 -0
  11. tokenizer_config.json +59 -0
  12. vocab.txt +0 -0
README.md CHANGED
@@ -1,3 +1,555 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/paraphrase-mpnet-base-v2
10
+ metrics:
11
+ - accuracy
12
+ widget:
13
+ - text: food portions:The food portions are quite filling, but not too much.
14
+ - text: waiters:The waiters are quite alert in helping customers, but cannot always
15
+ answer all questions in detail.
16
+ - text: experience:The atmosphere here is pleasant, although it doesn't provide an
17
+ extraordinary experience.
18
+ - text: food:The food does not have a distinctive taste.
19
+ - text: restaurant atmosphere:The restaurant atmosphere is too stiff and unpleasant.
20
+ pipeline_tag: text-classification
21
+ inference: false
22
+ model-index:
23
+ - name: SetFit Aspect Model with sentence-transformers/paraphrase-mpnet-base-v2
24
+ results:
25
+ - task:
26
+ type: text-classification
27
+ name: Text Classification
28
+ dataset:
29
+ name: Unknown
30
+ type: unknown
31
+ split: test
32
+ metrics:
33
+ - type: accuracy
34
+ value: 1.0
35
+ name: Accuracy
36
+ ---
37
+
38
+ # SetFit Aspect Model with sentence-transformers/paraphrase-mpnet-base-v2
39
+
40
+ 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/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. In particular, this model is in charge of filtering aspect span candidates.
41
+
42
+ The model has been trained using an efficient few-shot learning technique that involves:
43
+
44
+ 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
45
+ 2. Training a classification head with features from the fine-tuned Sentence Transformer.
46
+
47
+ This model was trained within the context of a larger system for ABSA, which looks like so:
48
+
49
+ 1. Use a spaCy model to select possible aspect span candidates.
50
+ 2. **Use this SetFit model to filter these possible aspect span candidates.**
51
+ 3. Use a SetFit model to classify the filtered aspect span candidates.
52
+
53
+ ## Model Details
54
+
55
+ ### Model Description
56
+ - **Model Type:** SetFit
57
+ - **Sentence Transformer body:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2)
58
+ - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
59
+ - **spaCy Model:** en_core_web_lg
60
+ - **SetFitABSA Aspect Model:** [models/en-setfit-absa-model-aspect](https://huggingface.co/models/en-setfit-absa-model-aspect)
61
+ - **SetFitABSA Polarity Model:** [models/en-setfit-absa-model-polarity](https://huggingface.co/models/en-setfit-absa-model-polarity)
62
+ - **Maximum Sequence Length:** 512 tokens
63
+ - **Number of Classes:** 2 classes
64
+ <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
65
+ <!-- - **Language:** Unknown -->
66
+ <!-- - **License:** Unknown -->
67
+
68
+ ### Model Sources
69
+
70
+ - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
71
+ - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
72
+ - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
73
+
74
+ ### Model Labels
75
+ | Label | Examples |
76
+ |:----------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
77
+ | no aspect | <ul><li>'food:The food is really delicious! The meat is tender and the spices are well seasoned. I will definitely come back again.'</li><li>'meat:The food is really delicious! The meat is tender and the spices are well seasoned. I will definitely come back again.'</li><li>'spices:The food is really delicious! The meat is tender and the spices are well seasoned. I will definitely come back again.'</li></ul> |
78
+ | aspect | <ul><li>'Service:Service is standard, nothing extraordinary.'</li><li>'Service:Service from the staff is very friendly.'</li><li>'Service:Service from the staff is very fast and professional.'</li></ul> |
79
+
80
+ ## Evaluation
81
+
82
+ ### Metrics
83
+ | Label | Accuracy |
84
+ |:--------|:---------|
85
+ | **all** | 1.0 |
86
+
87
+ ## Uses
88
+
89
+ ### Direct Use for Inference
90
+
91
+ First install the SetFit library:
92
+
93
+ ```bash
94
+ pip install setfit
95
+ ```
96
+
97
+ Then you can load this model and run inference.
98
+
99
+ ```python
100
+ from setfit import AbsaModel
101
+
102
+ # Download from the 🤗 Hub
103
+ model = AbsaModel.from_pretrained(
104
+ "models/en-setfit-absa-model-aspect",
105
+ "models/en-setfit-absa-model-polarity",
106
+ )
107
+ # Run inference
108
+ preds = model("The food was great, but the venue is just way too busy.")
109
+ ```
110
+
111
+ <!--
112
+ ### Downstream Use
113
+
114
+ *List how someone could finetune this model on their own dataset.*
115
+ -->
116
+
117
+ <!--
118
+ ### Out-of-Scope Use
119
+
120
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
121
+ -->
122
+
123
+ <!--
124
+ ## Bias, Risks and Limitations
125
+
126
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
127
+ -->
128
+
129
+ <!--
130
+ ### Recommendations
131
+
132
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
133
+ -->
134
+
135
+ ## Training Details
136
+
137
+ ### Training Set Metrics
138
+ | Training set | Min | Median | Max |
139
+ |:-------------|:----|:--------|:----|
140
+ | Word count | 4 | 14.3487 | 72 |
141
+
142
+ | Label | Training Sample Count |
143
+ |:----------|:----------------------|
144
+ | no aspect | 1701 |
145
+ | aspect | 14 |
146
+
147
+ ### Training Hyperparameters
148
+ - batch_size: (4, 4)
149
+ - num_epochs: (1, 1)
150
+ - max_steps: -1
151
+ - sampling_strategy: oversampling
152
+ - num_iterations: 20
153
+ - body_learning_rate: (2e-05, 1e-05)
154
+ - head_learning_rate: 0.01
155
+ - loss: CosineSimilarityLoss
156
+ - distance_metric: cosine_distance
157
+ - margin: 0.25
158
+ - end_to_end: False
159
+ - use_amp: False
160
+ - warmup_proportion: 0.1
161
+ - seed: 42
162
+ - eval_max_steps: -1
163
+ - load_best_model_at_end: False
164
+
165
+ ### Training Results
166
+ | Epoch | Step | Training Loss | Validation Loss |
167
+ |:------:|:-----:|:-------------:|:---------------:|
168
+ | 0.0001 | 1 | 0.34 | - |
169
+ | 0.0029 | 50 | 0.318 | - |
170
+ | 0.0058 | 100 | 0.2344 | - |
171
+ | 0.0087 | 150 | 0.1925 | - |
172
+ | 0.0117 | 200 | 0.1893 | - |
173
+ | 0.0146 | 250 | 0.014 | - |
174
+ | 0.0175 | 300 | 0.0017 | - |
175
+ | 0.0204 | 350 | 0.0041 | - |
176
+ | 0.0233 | 400 | 0.0008 | - |
177
+ | 0.0262 | 450 | 0.0008 | - |
178
+ | 0.0292 | 500 | 0.0003 | - |
179
+ | 0.0321 | 550 | 0.0003 | - |
180
+ | 0.0350 | 600 | 0.0004 | - |
181
+ | 0.0379 | 650 | 0.0004 | - |
182
+ | 0.0408 | 700 | 0.0004 | - |
183
+ | 0.0437 | 750 | 0.0008 | - |
184
+ | 0.0466 | 800 | 0.0004 | - |
185
+ | 0.0496 | 850 | 0.0002 | - |
186
+ | 0.0525 | 900 | 0.0003 | - |
187
+ | 0.0554 | 950 | 0.0001 | - |
188
+ | 0.0583 | 1000 | 0.0001 | - |
189
+ | 0.0612 | 1050 | 0.0002 | - |
190
+ | 0.0641 | 1100 | 0.0002 | - |
191
+ | 0.0671 | 1150 | 0.0002 | - |
192
+ | 0.0700 | 1200 | 0.0001 | - |
193
+ | 0.0729 | 1250 | 0.0002 | - |
194
+ | 0.0758 | 1300 | 0.0001 | - |
195
+ | 0.0787 | 1350 | 0.0 | - |
196
+ | 0.0816 | 1400 | 0.0001 | - |
197
+ | 0.0845 | 1450 | 0.0001 | - |
198
+ | 0.0875 | 1500 | 0.0001 | - |
199
+ | 0.0904 | 1550 | 0.0001 | - |
200
+ | 0.0933 | 1600 | 0.0001 | - |
201
+ | 0.0962 | 1650 | 0.0001 | - |
202
+ | 0.0991 | 1700 | 0.0 | - |
203
+ | 0.1020 | 1750 | 0.0001 | - |
204
+ | 0.1050 | 1800 | 0.0001 | - |
205
+ | 0.1079 | 1850 | 0.0001 | - |
206
+ | 0.1108 | 1900 | 0.0001 | - |
207
+ | 0.1137 | 1950 | 0.0 | - |
208
+ | 0.1166 | 2000 | 0.0001 | - |
209
+ | 0.1195 | 2050 | 0.0001 | - |
210
+ | 0.1224 | 2100 | 0.0 | - |
211
+ | 0.1254 | 2150 | 0.0006 | - |
212
+ | 0.1283 | 2200 | 0.0002 | - |
213
+ | 0.1312 | 2250 | 0.0 | - |
214
+ | 0.1341 | 2300 | 0.0 | - |
215
+ | 0.1370 | 2350 | 0.2106 | - |
216
+ | 0.1399 | 2400 | 0.0 | - |
217
+ | 0.1429 | 2450 | 0.0001 | - |
218
+ | 0.1458 | 2500 | 0.0001 | - |
219
+ | 0.1487 | 2550 | 0.0 | - |
220
+ | 0.1516 | 2600 | 0.0 | - |
221
+ | 0.1545 | 2650 | 0.0 | - |
222
+ | 0.1574 | 2700 | 0.0 | - |
223
+ | 0.1603 | 2750 | 0.0 | - |
224
+ | 0.1633 | 2800 | 0.0 | - |
225
+ | 0.1662 | 2850 | 0.0001 | - |
226
+ | 0.1691 | 2900 | 0.0 | - |
227
+ | 0.1720 | 2950 | 0.0 | - |
228
+ | 0.1749 | 3000 | 0.0 | - |
229
+ | 0.1778 | 3050 | 0.0001 | - |
230
+ | 0.1808 | 3100 | 0.0 | - |
231
+ | 0.1837 | 3150 | 0.0 | - |
232
+ | 0.1866 | 3200 | 0.0001 | - |
233
+ | 0.1895 | 3250 | 0.0 | - |
234
+ | 0.1924 | 3300 | 0.0001 | - |
235
+ | 0.1953 | 3350 | 0.0001 | - |
236
+ | 0.1983 | 3400 | 0.0 | - |
237
+ | 0.2012 | 3450 | 0.0 | - |
238
+ | 0.2041 | 3500 | 0.0 | - |
239
+ | 0.2070 | 3550 | 0.0 | - |
240
+ | 0.2099 | 3600 | 0.0 | - |
241
+ | 0.2128 | 3650 | 0.0 | - |
242
+ | 0.2157 | 3700 | 0.0 | - |
243
+ | 0.2187 | 3750 | 0.0 | - |
244
+ | 0.2216 | 3800 | 0.0 | - |
245
+ | 0.2245 | 3850 | 0.0 | - |
246
+ | 0.2274 | 3900 | 0.0 | - |
247
+ | 0.2303 | 3950 | 0.0 | - |
248
+ | 0.2332 | 4000 | 0.0 | - |
249
+ | 0.2362 | 4050 | 0.0 | - |
250
+ | 0.2391 | 4100 | 0.0 | - |
251
+ | 0.2420 | 4150 | 0.0 | - |
252
+ | 0.2449 | 4200 | 0.0 | - |
253
+ | 0.2478 | 4250 | 0.0 | - |
254
+ | 0.2507 | 4300 | 0.0 | - |
255
+ | 0.2536 | 4350 | 0.0 | - |
256
+ | 0.2566 | 4400 | 0.0 | - |
257
+ | 0.2595 | 4450 | 0.0 | - |
258
+ | 0.2624 | 4500 | 0.0 | - |
259
+ | 0.2653 | 4550 | 0.0 | - |
260
+ | 0.2682 | 4600 | 0.0 | - |
261
+ | 0.2711 | 4650 | 0.0 | - |
262
+ | 0.2741 | 4700 | 0.0001 | - |
263
+ | 0.2770 | 4750 | 0.0 | - |
264
+ | 0.2799 | 4800 | 0.0 | - |
265
+ | 0.2828 | 4850 | 0.0 | - |
266
+ | 0.2857 | 4900 | 0.0 | - |
267
+ | 0.2886 | 4950 | 0.0 | - |
268
+ | 0.2915 | 5000 | 0.0 | - |
269
+ | 0.2945 | 5050 | 0.0 | - |
270
+ | 0.2974 | 5100 | 0.0 | - |
271
+ | 0.3003 | 5150 | 0.0 | - |
272
+ | 0.3032 | 5200 | 0.0 | - |
273
+ | 0.3061 | 5250 | 0.0 | - |
274
+ | 0.3090 | 5300 | 0.0 | - |
275
+ | 0.3120 | 5350 | 0.0 | - |
276
+ | 0.3149 | 5400 | 0.0 | - |
277
+ | 0.3178 | 5450 | 0.0 | - |
278
+ | 0.3207 | 5500 | 0.0 | - |
279
+ | 0.3236 | 5550 | 0.0 | - |
280
+ | 0.3265 | 5600 | 0.0 | - |
281
+ | 0.3294 | 5650 | 0.0 | - |
282
+ | 0.3324 | 5700 | 0.0 | - |
283
+ | 0.3353 | 5750 | 0.0 | - |
284
+ | 0.3382 | 5800 | 0.0 | - |
285
+ | 0.3411 | 5850 | 0.0 | - |
286
+ | 0.3440 | 5900 | 0.0 | - |
287
+ | 0.3469 | 5950 | 0.0 | - |
288
+ | 0.3499 | 6000 | 0.0 | - |
289
+ | 0.3528 | 6050 | 0.0 | - |
290
+ | 0.3557 | 6100 | 0.0 | - |
291
+ | 0.3586 | 6150 | 0.0 | - |
292
+ | 0.3615 | 6200 | 0.0 | - |
293
+ | 0.3644 | 6250 | 0.0 | - |
294
+ | 0.3673 | 6300 | 0.0 | - |
295
+ | 0.3703 | 6350 | 0.0 | - |
296
+ | 0.3732 | 6400 | 0.0001 | - |
297
+ | 0.3761 | 6450 | 0.0 | - |
298
+ | 0.3790 | 6500 | 0.0 | - |
299
+ | 0.3819 | 6550 | 0.0 | - |
300
+ | 0.3848 | 6600 | 0.0 | - |
301
+ | 0.3878 | 6650 | 0.0 | - |
302
+ | 0.3907 | 6700 | 0.0 | - |
303
+ | 0.3936 | 6750 | 0.0 | - |
304
+ | 0.3965 | 6800 | 0.0 | - |
305
+ | 0.3994 | 6850 | 0.0 | - |
306
+ | 0.4023 | 6900 | 0.0 | - |
307
+ | 0.4052 | 6950 | 0.0 | - |
308
+ | 0.4082 | 7000 | 0.0 | - |
309
+ | 0.4111 | 7050 | 0.0 | - |
310
+ | 0.4140 | 7100 | 0.0001 | - |
311
+ | 0.4169 | 7150 | 0.0 | - |
312
+ | 0.4198 | 7200 | 0.0 | - |
313
+ | 0.4227 | 7250 | 0.0 | - |
314
+ | 0.4257 | 7300 | 0.0 | - |
315
+ | 0.4286 | 7350 | 0.0 | - |
316
+ | 0.4315 | 7400 | 0.0 | - |
317
+ | 0.4344 | 7450 | 0.0 | - |
318
+ | 0.4373 | 7500 | 0.0 | - |
319
+ | 0.4402 | 7550 | 0.0 | - |
320
+ | 0.4431 | 7600 | 0.0 | - |
321
+ | 0.4461 | 7650 | 0.0 | - |
322
+ | 0.4490 | 7700 | 0.0 | - |
323
+ | 0.4519 | 7750 | 0.0 | - |
324
+ | 0.4548 | 7800 | 0.0 | - |
325
+ | 0.4577 | 7850 | 0.0 | - |
326
+ | 0.4606 | 7900 | 0.0 | - |
327
+ | 0.4636 | 7950 | 0.0 | - |
328
+ | 0.4665 | 8000 | 0.0 | - |
329
+ | 0.4694 | 8050 | 0.0 | - |
330
+ | 0.4723 | 8100 | 0.0 | - |
331
+ | 0.4752 | 8150 | 0.0 | - |
332
+ | 0.4781 | 8200 | 0.0 | - |
333
+ | 0.4810 | 8250 | 0.0 | - |
334
+ | 0.4840 | 8300 | 0.0 | - |
335
+ | 0.4869 | 8350 | 0.0001 | - |
336
+ | 0.4898 | 8400 | 0.0 | - |
337
+ | 0.4927 | 8450 | 0.0 | - |
338
+ | 0.4956 | 8500 | 0.0 | - |
339
+ | 0.4985 | 8550 | 0.0 | - |
340
+ | 0.5015 | 8600 | 0.0 | - |
341
+ | 0.5044 | 8650 | 0.0 | - |
342
+ | 0.5073 | 8700 | 0.0 | - |
343
+ | 0.5102 | 8750 | 0.0 | - |
344
+ | 0.5131 | 8800 | 0.0 | - |
345
+ | 0.5160 | 8850 | 0.0 | - |
346
+ | 0.5190 | 8900 | 0.0 | - |
347
+ | 0.5219 | 8950 | 0.0 | - |
348
+ | 0.5248 | 9000 | 0.0 | - |
349
+ | 0.5277 | 9050 | 0.0 | - |
350
+ | 0.5306 | 9100 | 0.0 | - |
351
+ | 0.5335 | 9150 | 0.0 | - |
352
+ | 0.5364 | 9200 | 0.0 | - |
353
+ | 0.5394 | 9250 | 0.0 | - |
354
+ | 0.5423 | 9300 | 0.0 | - |
355
+ | 0.5452 | 9350 | 0.0 | - |
356
+ | 0.5481 | 9400 | 0.0 | - |
357
+ | 0.5510 | 9450 | 0.0 | - |
358
+ | 0.5539 | 9500 | 0.0 | - |
359
+ | 0.5569 | 9550 | 0.0 | - |
360
+ | 0.5598 | 9600 | 0.0 | - |
361
+ | 0.5627 | 9650 | 0.0 | - |
362
+ | 0.5656 | 9700 | 0.0 | - |
363
+ | 0.5685 | 9750 | 0.0 | - |
364
+ | 0.5714 | 9800 | 0.0 | - |
365
+ | 0.5743 | 9850 | 0.0 | - |
366
+ | 0.5773 | 9900 | 0.0 | - |
367
+ | 0.5802 | 9950 | 0.0 | - |
368
+ | 0.5831 | 10000 | 0.0 | - |
369
+ | 0.5860 | 10050 | 0.0 | - |
370
+ | 0.5889 | 10100 | 0.0 | - |
371
+ | 0.5918 | 10150 | 0.0 | - |
372
+ | 0.5948 | 10200 | 0.0 | - |
373
+ | 0.5977 | 10250 | 0.0 | - |
374
+ | 0.6006 | 10300 | 0.0 | - |
375
+ | 0.6035 | 10350 | 0.0 | - |
376
+ | 0.6064 | 10400 | 0.0 | - |
377
+ | 0.6093 | 10450 | 0.0 | - |
378
+ | 0.6122 | 10500 | 0.0 | - |
379
+ | 0.6152 | 10550 | 0.0 | - |
380
+ | 0.6181 | 10600 | 0.0 | - |
381
+ | 0.6210 | 10650 | 0.0 | - |
382
+ | 0.6239 | 10700 | 0.0 | - |
383
+ | 0.6268 | 10750 | 0.0 | - |
384
+ | 0.6297 | 10800 | 0.0 | - |
385
+ | 0.6327 | 10850 | 0.0 | - |
386
+ | 0.6356 | 10900 | 0.0 | - |
387
+ | 0.6385 | 10950 | 0.0 | - |
388
+ | 0.6414 | 11000 | 0.0 | - |
389
+ | 0.6443 | 11050 | 0.0 | - |
390
+ | 0.6472 | 11100 | 0.0 | - |
391
+ | 0.6501 | 11150 | 0.0 | - |
392
+ | 0.6531 | 11200 | 0.0 | - |
393
+ | 0.6560 | 11250 | 0.0 | - |
394
+ | 0.6589 | 11300 | 0.0 | - |
395
+ | 0.6618 | 11350 | 0.0 | - |
396
+ | 0.6647 | 11400 | 0.0 | - |
397
+ | 0.6676 | 11450 | 0.0 | - |
398
+ | 0.6706 | 11500 | 0.0 | - |
399
+ | 0.6735 | 11550 | 0.0 | - |
400
+ | 0.6764 | 11600 | 0.0 | - |
401
+ | 0.6793 | 11650 | 0.0 | - |
402
+ | 0.6822 | 11700 | 0.0 | - |
403
+ | 0.6851 | 11750 | 0.0 | - |
404
+ | 0.6880 | 11800 | 0.0 | - |
405
+ | 0.6910 | 11850 | 0.0 | - |
406
+ | 0.6939 | 11900 | 0.0 | - |
407
+ | 0.6968 | 11950 | 0.0 | - |
408
+ | 0.6997 | 12000 | 0.0 | - |
409
+ | 0.7026 | 12050 | 0.0 | - |
410
+ | 0.7055 | 12100 | 0.0 | - |
411
+ | 0.7085 | 12150 | 0.0 | - |
412
+ | 0.7114 | 12200 | 0.0 | - |
413
+ | 0.7143 | 12250 | 0.0 | - |
414
+ | 0.7172 | 12300 | 0.0 | - |
415
+ | 0.7201 | 12350 | 0.0 | - |
416
+ | 0.7230 | 12400 | 0.0 | - |
417
+ | 0.7259 | 12450 | 0.0 | - |
418
+ | 0.7289 | 12500 | 0.0 | - |
419
+ | 0.7318 | 12550 | 0.0 | - |
420
+ | 0.7347 | 12600 | 0.0 | - |
421
+ | 0.7376 | 12650 | 0.0 | - |
422
+ | 0.7405 | 12700 | 0.0 | - |
423
+ | 0.7434 | 12750 | 0.0 | - |
424
+ | 0.7464 | 12800 | 0.0 | - |
425
+ | 0.7493 | 12850 | 0.0 | - |
426
+ | 0.7522 | 12900 | 0.0 | - |
427
+ | 0.7551 | 12950 | 0.0 | - |
428
+ | 0.7580 | 13000 | 0.0 | - |
429
+ | 0.7609 | 13050 | 0.0 | - |
430
+ | 0.7638 | 13100 | 0.0 | - |
431
+ | 0.7668 | 13150 | 0.0 | - |
432
+ | 0.7697 | 13200 | 0.0 | - |
433
+ | 0.7726 | 13250 | 0.0 | - |
434
+ | 0.7755 | 13300 | 0.0 | - |
435
+ | 0.7784 | 13350 | 0.0 | - |
436
+ | 0.7813 | 13400 | 0.0 | - |
437
+ | 0.7843 | 13450 | 0.0 | - |
438
+ | 0.7872 | 13500 | 0.0 | - |
439
+ | 0.7901 | 13550 | 0.0 | - |
440
+ | 0.7930 | 13600 | 0.0 | - |
441
+ | 0.7959 | 13650 | 0.0 | - |
442
+ | 0.7988 | 13700 | 0.0 | - |
443
+ | 0.8017 | 13750 | 0.0 | - |
444
+ | 0.8047 | 13800 | 0.0 | - |
445
+ | 0.8076 | 13850 | 0.0 | - |
446
+ | 0.8105 | 13900 | 0.0 | - |
447
+ | 0.8134 | 13950 | 0.0 | - |
448
+ | 0.8163 | 14000 | 0.0 | - |
449
+ | 0.8192 | 14050 | 0.0 | - |
450
+ | 0.8222 | 14100 | 0.0 | - |
451
+ | 0.8251 | 14150 | 0.0 | - |
452
+ | 0.8280 | 14200 | 0.0 | - |
453
+ | 0.8309 | 14250 | 0.0 | - |
454
+ | 0.8338 | 14300 | 0.0 | - |
455
+ | 0.8367 | 14350 | 0.0 | - |
456
+ | 0.8397 | 14400 | 0.0 | - |
457
+ | 0.8426 | 14450 | 0.0 | - |
458
+ | 0.8455 | 14500 | 0.0 | - |
459
+ | 0.8484 | 14550 | 0.0 | - |
460
+ | 0.8513 | 14600 | 0.0 | - |
461
+ | 0.8542 | 14650 | 0.0 | - |
462
+ | 0.8571 | 14700 | 0.0 | - |
463
+ | 0.8601 | 14750 | 0.0 | - |
464
+ | 0.8630 | 14800 | 0.0 | - |
465
+ | 0.8659 | 14850 | 0.0 | - |
466
+ | 0.8688 | 14900 | 0.0 | - |
467
+ | 0.8717 | 14950 | 0.0 | - |
468
+ | 0.8746 | 15000 | 0.0 | - |
469
+ | 0.8776 | 15050 | 0.0 | - |
470
+ | 0.8805 | 15100 | 0.0 | - |
471
+ | 0.8834 | 15150 | 0.0 | - |
472
+ | 0.8863 | 15200 | 0.0 | - |
473
+ | 0.8892 | 15250 | 0.0 | - |
474
+ | 0.8921 | 15300 | 0.0 | - |
475
+ | 0.8950 | 15350 | 0.0 | - |
476
+ | 0.8980 | 15400 | 0.0 | - |
477
+ | 0.9009 | 15450 | 0.0 | - |
478
+ | 0.9038 | 15500 | 0.0 | - |
479
+ | 0.9067 | 15550 | 0.0 | - |
480
+ | 0.9096 | 15600 | 0.0 | - |
481
+ | 0.9125 | 15650 | 0.0 | - |
482
+ | 0.9155 | 15700 | 0.0 | - |
483
+ | 0.9184 | 15750 | 0.0 | - |
484
+ | 0.9213 | 15800 | 0.0 | - |
485
+ | 0.9242 | 15850 | 0.0 | - |
486
+ | 0.9271 | 15900 | 0.0 | - |
487
+ | 0.9300 | 15950 | 0.0 | - |
488
+ | 0.9329 | 16000 | 0.0 | - |
489
+ | 0.9359 | 16050 | 0.0 | - |
490
+ | 0.9388 | 16100 | 0.0 | - |
491
+ | 0.9417 | 16150 | 0.0 | - |
492
+ | 0.9446 | 16200 | 0.0 | - |
493
+ | 0.9475 | 16250 | 0.0 | - |
494
+ | 0.9504 | 16300 | 0.0 | - |
495
+ | 0.9534 | 16350 | 0.0 | - |
496
+ | 0.9563 | 16400 | 0.0 | - |
497
+ | 0.9592 | 16450 | 0.0 | - |
498
+ | 0.9621 | 16500 | 0.0 | - |
499
+ | 0.9650 | 16550 | 0.0 | - |
500
+ | 0.9679 | 16600 | 0.0 | - |
501
+ | 0.9708 | 16650 | 0.0 | - |
502
+ | 0.9738 | 16700 | 0.0 | - |
503
+ | 0.9767 | 16750 | 0.0 | - |
504
+ | 0.9796 | 16800 | 0.0 | - |
505
+ | 0.9825 | 16850 | 0.0 | - |
506
+ | 0.9854 | 16900 | 0.0 | - |
507
+ | 0.9883 | 16950 | 0.0 | - |
508
+ | 0.9913 | 17000 | 0.0 | - |
509
+ | 0.9942 | 17050 | 0.0 | - |
510
+ | 0.9971 | 17100 | 0.0 | - |
511
+ | 1.0 | 17150 | 0.0 | - |
512
+
513
+ ### Framework Versions
514
+ - Python: 3.10.13
515
+ - SetFit: 1.0.3
516
+ - Sentence Transformers: 2.7.0
517
+ - spaCy: 3.7.4
518
+ - Transformers: 4.39.3
519
+ - PyTorch: 2.1.2
520
+ - Datasets: 2.18.0
521
+ - Tokenizers: 0.15.2
522
+
523
+ ## Citation
524
+
525
+ ### BibTeX
526
+ ```bibtex
527
+ @article{https://doi.org/10.48550/arxiv.2209.11055,
528
+ doi = {10.48550/ARXIV.2209.11055},
529
+ url = {https://arxiv.org/abs/2209.11055},
530
+ author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
531
+ keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
532
+ title = {Efficient Few-Shot Learning Without Prompts},
533
+ publisher = {arXiv},
534
+ year = {2022},
535
+ copyright = {Creative Commons Attribution 4.0 International}
536
+ }
537
+ ```
538
+
539
+ <!--
540
+ ## Glossary
541
+
542
+ *Clearly define terms in order to be accessible across audiences.*
543
+ -->
544
+
545
+ <!--
546
+ ## Model Card Authors
547
+
548
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
549
+ -->
550
+
551
+ <!--
552
+ ## Model Card Contact
553
+
554
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
555
+ -->
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": "4.39.3",
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": "4.7.0",
5
+ "pytorch": "1.9.0+cu102"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null
9
+ }
config_setfit.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "labels": [
3
+ "no aspect",
4
+ "aspect"
5
+ ],
6
+ "spacy_model": "en_core_web_lg",
7
+ "span_context": 0,
8
+ "normalize_embeddings": false
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef44edb83ebb83a813942861abf73da10b810f4ab36a3e79618e486f1895893f
3
+ size 437967672
model_head.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6dce6906de3149da54eff2b6fcf60ebb8bc1e85c3f196ec2af51102969d700a
3
+ size 6991
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