Hugging Face's logo

NazmusAshrafi
/
setfit-MiniLM-mpnet-absa-tesla-tweet-aspect

Text Classification
setfit
Safetensors
sentence-transformers
mpnet
absa
generated_from_setfit_trainer
Eval Results
Model card Files Community
NazmusAshrafi commited on
Commit
ee10475
•
1 Parent(s): 8c91056

Add SetFit ABSA model

Browse files
Files changed (13) hide show
  1. 1_Pooling/config.json +7 -0
  2. README.md +618 -1
  3. config.json +24 -0
  4. config_sentence_transformers.json +7 -0
  5. config_setfit.json +9 -0
  6. model.safetensors +3 -0
  7. model_head.pkl +3 -0
  8. modules.json +14 -0
  9. sentence_bert_config.json +4 -0
  10. special_tokens_map.json +51 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +59 -0
  13. vocab.txt +0 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
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
+ }
README.md CHANGED
@@ -1,3 +1,620 @@
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
+ metrics:
10
+ - accuracy
11
+ widget:
12
+ - text: EPS:Why do I invest in $TSLA? Do I have blind faith? No. I closely watch their
13
+ EPS, their P/E, their products, their forecast. This is the only investment I
14
+ KNOW. And I know this is a great investment. I don’t say this to convince anyone.
15
+ These are my thoughts about my investment.
16
+ - text: EPS:$TSLA at 57x Street 2023 EPS (45x my 2023 EPS) seems an absurd valuation
17
+ for 50%+ volume/EPS growth fueled by the dual tailwinds of soaring EV adoption
18
+ and TSLA capacity. Investors seem overly worried Elon will sell more TSLA shares
19
+ even though he says “no further sales planned.” https://t.co/80siAfL847
20
+ - text: 'TSLA:Cars ... for delivery ? Most likely so. $TSLA #GigaBerlin https://t.co/XL6auHEYjZ'
21
+ - text: companies:Mainstream media has done an amazing job at brainwashing people.
22
+ Today at work, we were asked what companies we believe in & I said @Tesla
23
+ because they make the safest cars & EVERYONE disagreed with me because they
24
+ heard“they catch on fire & the batteries cost 20k to replace”
25
+ - text: 'cash flow:The market won’t be able to hold Tesla stock down longer, once
26
+ all factories are ramping and in full production.
27
+
28
+
29
+ There’s a certain point where the # of cars being produced, revenue & profit
30
+ & cash flow generated makes the valuation of Tesla look ridiculous.
31
+
32
+
33
+ $TSLA #Tesla'
34
+ pipeline_tag: text-classification
35
+ inference: false
36
+ base_model: sentence-transformers/paraphrase-mpnet-base-v2
37
+ model-index:
38
+ - name: SetFit Aspect Model with sentence-transformers/paraphrase-mpnet-base-v2
39
+ results:
40
+ - task:
41
+ type: text-classification
42
+ name: Text Classification
43
+ dataset:
44
+ name: Unknown
45
+ type: unknown
46
+ split: test
47
+ metrics:
48
+ - type: accuracy
49
+ value: 0.9798115746971736
50
+ name: Accuracy
51
  ---
52
+
53
+ # SetFit Aspect Model with sentence-transformers/paraphrase-mpnet-base-v2
54
+
55
+ 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.
56
+
57
+ The model has been trained using an efficient few-shot learning technique that involves:
58
+
59
+ 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
60
+ 2. Training a classification head with features from the fine-tuned Sentence Transformer.
61
+
62
+ This model was trained within the context of a larger system for ABSA, which looks like so:
63
+
64
+ 1. Use a spaCy model to select possible aspect span candidates.
65
+ 2. **Use this SetFit model to filter these possible aspect span candidates.**
66
+ 3. Use a SetFit model to classify the filtered aspect span candidates.
67
+
68
+ ## Model Details
69
+
70
+ ### Model Description
71
+ - **Model Type:** SetFit
72
+ - **Sentence Transformer body:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2)
73
+ - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
74
+ - **spaCy Model:** en_core_web_lg
75
+ - **SetFitABSA Aspect Model:** [NazmusAshrafi/setfit-MiniLM-mpnet-absa-tesla-tweet-aspect](https://huggingface.co/NazmusAshrafi/setfit-MiniLM-mpnet-absa-tesla-tweet-aspect)
76
+ - **SetFitABSA Polarity Model:** [NazmusAshrafi/setfit-MiniLM-mpnet-absa-tesla-tweet-polarity](https://huggingface.co/NazmusAshrafi/setfit-MiniLM-mpnet-absa-tesla-tweet-polarity)
77
+ - **Maximum Sequence Length:** 512 tokens
78
+ - **Number of Classes:** 2 classes
79
+ <!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
80
+ <!-- - **Language:** Unknown -->
81
+ <!-- - **License:** Unknown -->
82
+
83
+ ### Model Sources
84
+
85
+ - **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
86
+ - **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
87
+ - **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
88
+
89
+ ### Model Labels
90
+ | Label | Examples |
91
+ |:----------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
92
+ | no aspect | <ul><li>'Tesla:Tesla could deliver 500K+ vehicles in Q4, increasing annual deliveries by 50%. Due to headwinds in 2022, now the manufacturer is ramping up production even harder to get as many EVs on the road as possible\n\n #Tesla $TSLA \nhttps://t.co/b2NCtZqDYn'</li><li>'vehicles:Tesla could deliver 500K+ vehicles in Q4, increasing annual deliveries by 50%. Due to headwinds in 2022, now the manufacturer is ramping up production even harder to get as many EVs on the road as possible\n\n #Tesla $TSLA \nhttps://t.co/b2NCtZqDYn'</li><li>'Q4:Tesla could deliver 500K+ vehicles in Q4, increasing annual deliveries by 50%. Due to headwinds in 2022, now the manufacturer is ramping up production even harder to get as many EVs on the road as possible\n\n #Tesla $TSLA \nhttps://t.co/b2NCtZqDYn'</li></ul> |
93
+ | aspect | <ul><li>"profit:I'm pretty sure, all an EV tax incentive will do, is raise the price of Teslas, at least for the next few years.\n\ni.e. just more profit for $TSLA\nAs if demand wasn't abundant enough already."</li><li>"price:I'm pretty sure, all an EV tax incentive will do, is raise the price of Teslas, at least for the next few years.\n\ni.e. just more profit for $TSLA\nAs if demand wasn't abundant enough already."</li><li>'car:John Hennessey gets a $TSLA Plaid. \nA retired OEM executive describes Tesla as a $30k car with $70k in batteries. \nThe perfect description of a Tesla https://t.co/m5J5m3AuMJ'</li></ul> |
94
+
95
+ ## Evaluation
96
+
97
+ ### Metrics
98
+ | Label | Accuracy |
99
+ |:--------|:---------|
100
+ | **all** | 0.9798 |
101
+
102
+ ## Uses
103
+
104
+ ### Direct Use for Inference
105
+
106
+ First install the SetFit library:
107
+
108
+ ```bash
109
+ pip install setfit
110
+ ```
111
+
112
+ Then you can load this model and run inference.
113
+
114
+ ```python
115
+ from setfit import AbsaModel
116
+
117
+ # Download from the 🤗 Hub
118
+ model = AbsaModel.from_pretrained(
119
+ "NazmusAshrafi/setfit-MiniLM-mpnet-absa-tesla-tweet-aspect",
120
+ "NazmusAshrafi/setfit-MiniLM-mpnet-absa-tesla-tweet-polarity",
121
+ )
122
+ # Run inference
123
+ preds = model("The food was great, but the venue is just way too busy.")
124
+ ```
125
+
126
+ <!--
127
+ ### Downstream Use
128
+
129
+ *List how someone could finetune this model on their own dataset.*
130
+ -->
131
+
132
+ <!--
133
+ ### Out-of-Scope Use
134
+
135
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
136
+ -->
137
+
138
+ <!--
139
+ ## Bias, Risks and Limitations
140
+
141
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
142
+ -->
143
+
144
+ <!--
145
+ ### Recommendations
146
+
147
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
148
+ -->
149
+
150
+ ## Training Details
151
+
152
+ ### Training Set Metrics
153
+ | Training set | Min | Median | Max |
154
+ |:-------------|:----|:--------|:----|
155
+ | Word count | 11 | 41.4789 | 57 |
156
+
157
+ | Label | Training Sample Count |
158
+ |:----------|:----------------------|
159
+ | no aspect | 560 |
160
+ | aspect | 33 |
161
+
162
+ ### Training Hyperparameters
163
+ - batch_size: (16, 2)
164
+ - num_epochs: (1, 16)
165
+ - max_steps: -1
166
+ - sampling_strategy: oversampling
167
+ - body_learning_rate: (2e-05, 1e-05)
168
+ - head_learning_rate: 0.01
169
+ - loss: CosineSimilarityLoss
170
+ - distance_metric: cosine_distance
171
+ - margin: 0.25
172
+ - end_to_end: False
173
+ - use_amp: False
174
+ - warmup_proportion: 0.1
175
+ - seed: 42
176
+ - eval_max_steps: -1
177
+ - load_best_model_at_end: False
178
+
179
+ ### Training Results
180
+ | Epoch | Step | Training Loss | Validation Loss |
181
+ |:------:|:-----:|:-------------:|:---------------:|
182
+ | 0.0001 | 1 | 0.2511 | - |
183
+ | 0.0025 | 50 | 0.2558 | - |
184
+ | 0.0051 | 100 | 0.2147 | - |
185
+ | 0.0076 | 150 | 0.2265 | - |
186
+ | 0.0101 | 200 | 0.2474 | - |
187
+ | 0.0127 | 250 | 0.2286 | - |
188
+ | 0.0152 | 300 | 0.1717 | - |
189
+ | 0.0178 | 350 | 0.0737 | - |
190
+ | 0.0203 | 400 | 0.0231 | - |
191
+ | 0.0228 | 450 | 0.0069 | - |
192
+ | 0.0254 | 500 | 0.0032 | - |
193
+ | 0.0279 | 550 | 0.002 | - |
194
+ | 0.0304 | 600 | 0.0008 | - |
195
+ | 0.0330 | 650 | 0.0023 | - |
196
+ | 0.0355 | 700 | 0.002 | - |
197
+ | 0.0381 | 750 | 0.0008 | - |
198
+ | 0.0406 | 800 | 0.0019 | - |
199
+ | 0.0431 | 850 | 0.0003 | - |
200
+ | 0.0457 | 900 | 0.0004 | - |
201
+ | 0.0482 | 950 | 0.0005 | - |
202
+ | 0.0507 | 1000 | 0.0003 | - |
203
+ | 0.0533 | 1050 | 0.0006 | - |
204
+ | 0.0558 | 1100 | 0.0071 | - |
205
+ | 0.0584 | 1150 | 0.0001 | - |
206
+ | 0.0609 | 1200 | 0.0001 | - |
207
+ | 0.0634 | 1250 | 0.0001 | - |
208
+ | 0.0660 | 1300 | 0.0001 | - |
209
+ | 0.0685 | 1350 | 0.0004 | - |
210
+ | 0.0710 | 1400 | 0.0001 | - |
211
+ | 0.0736 | 1450 | 0.0002 | - |
212
+ | 0.0761 | 1500 | 0.0002 | - |
213
+ | 0.0787 | 1550 | 0.0002 | - |
214
+ | 0.0812 | 1600 | 0.0001 | - |
215
+ | 0.0837 | 1650 | 0.0001 | - |
216
+ | 0.0863 | 1700 | 0.0007 | - |
217
+ | 0.0888 | 1750 | 0.0001 | - |
218
+ | 0.0913 | 1800 | 0.0002 | - |
219
+ | 0.0939 | 1850 | 0.0011 | - |
220
+ | 0.0964 | 1900 | 0.0007 | - |
221
+ | 0.0990 | 1950 | 0.001 | - |
222
+ | 0.1015 | 2000 | 0.0003 | - |
223
+ | 0.1040 | 2050 | 0.0004 | - |
224
+ | 0.1066 | 2100 | 0.0006 | - |
225
+ | 0.1091 | 2150 | 0.0004 | - |
226
+ | 0.1116 | 2200 | 0.0 | - |
227
+ | 0.1142 | 2250 | 0.0 | - |
228
+ | 0.1167 | 2300 | 0.0001 | - |
229
+ | 0.1193 | 2350 | 0.0017 | - |
230
+ | 0.1218 | 2400 | 0.0007 | - |
231
+ | 0.1243 | 2450 | 0.0023 | - |
232
+ | 0.1269 | 2500 | 0.0 | - |
233
+ | 0.1294 | 2550 | 0.0 | - |
234
+ | 0.1319 | 2600 | 0.0007 | - |
235
+ | 0.1345 | 2650 | 0.0 | - |
236
+ | 0.1370 | 2700 | 0.0004 | - |
237
+ | 0.1396 | 2750 | 0.0001 | - |
238
+ | 0.1421 | 2800 | 0.0002 | - |
239
+ | 0.1446 | 2850 | 0.0019 | - |
240
+ | 0.1472 | 2900 | 0.0002 | - |
241
+ | 0.1497 | 2950 | 0.0001 | - |
242
+ | 0.1522 | 3000 | 0.0 | - |
243
+ | 0.1548 | 3050 | 0.0001 | - |
244
+ | 0.1573 | 3100 | 0.0 | - |
245
+ | 0.1598 | 3150 | 0.0001 | - |
246
+ | 0.1624 | 3200 | 0.0007 | - |
247
+ | 0.1649 | 3250 | 0.0 | - |
248
+ | 0.1675 | 3300 | 0.0002 | - |
249
+ | 0.1700 | 3350 | 0.0004 | - |
250
+ | 0.1725 | 3400 | 0.0 | - |
251
+ | 0.1751 | 3450 | 0.0 | - |
252
+ | 0.1776 | 3500 | 0.0 | - |
253
+ | 0.1801 | 3550 | 0.0 | - |
254
+ | 0.1827 | 3600 | 0.0001 | - |
255
+ | 0.1852 | 3650 | 0.0 | - |
256
+ | 0.1878 | 3700 | 0.0001 | - |
257
+ | 0.1903 | 3750 | 0.0 | - |
258
+ | 0.1928 | 3800 | 0.0 | - |
259
+ | 0.1954 | 3850 | 0.0 | - |
260
+ | 0.1979 | 3900 | 0.0 | - |
261
+ | 0.2004 | 3950 | 0.0 | - |
262
+ | 0.2030 | 4000 | 0.0 | - |
263
+ | 0.2055 | 4050 | 0.0019 | - |
264
+ | 0.2081 | 4100 | 0.0 | - |
265
+ | 0.2106 | 4150 | 0.0001 | - |
266
+ | 0.2131 | 4200 | 0.0 | - |
267
+ | 0.2157 | 4250 | 0.0 | - |
268
+ | 0.2182 | 4300 | 0.0 | - |
269
+ | 0.2207 | 4350 | 0.0 | - |
270
+ | 0.2233 | 4400 | 0.0005 | - |
271
+ | 0.2258 | 4450 | 0.0 | - |
272
+ | 0.2284 | 4500 | 0.0 | - |
273
+ | 0.2309 | 4550 | 0.0 | - |
274
+ | 0.2334 | 4600 | 0.0 | - |
275
+ | 0.2360 | 4650 | 0.0 | - |
276
+ | 0.2385 | 4700 | 0.0009 | - |
277
+ | 0.2410 | 4750 | 0.0 | - |
278
+ | 0.2436 | 4800 | 0.0 | - |
279
+ | 0.2461 | 4850 | 0.0 | - |
280
+ | 0.2487 | 4900 | 0.0002 | - |
281
+ | 0.2512 | 4950 | 0.0 | - |
282
+ | 0.2537 | 5000 | 0.0011 | - |
283
+ | 0.2563 | 5050 | 0.0 | - |
284
+ | 0.2588 | 5100 | 0.0 | - |
285
+ | 0.2613 | 5150 | 0.0 | - |
286
+ | 0.2639 | 5200 | 0.0 | - |
287
+ | 0.2664 | 5250 | 0.0 | - |
288
+ | 0.2690 | 5300 | 0.0 | - |
289
+ | 0.2715 | 5350 | 0.0026 | - |
290
+ | 0.2740 | 5400 | 0.0 | - |
291
+ | 0.2766 | 5450 | 0.0021 | - |
292
+ | 0.2791 | 5500 | 0.0 | - |
293
+ | 0.2816 | 5550 | 0.0001 | - |
294
+ | 0.2842 | 5600 | 0.0 | - |
295
+ | 0.2867 | 5650 | 0.0001 | - |
296
+ | 0.2893 | 5700 | 0.0 | - |
297
+ | 0.2918 | 5750 | 0.0 | - |
298
+ | 0.2943 | 5800 | 0.0 | - |
299
+ | 0.2969 | 5850 | 0.0 | - |
300
+ | 0.2994 | 5900 | 0.0 | - |
301
+ | 0.3019 | 5950 | 0.0 | - |
302
+ | 0.3045 | 6000 | 0.0 | - |
303
+ | 0.3070 | 6050 | 0.0 | - |
304
+ | 0.3096 | 6100 | 0.0 | - |
305
+ | 0.3121 | 6150 | 0.0003 | - |
306
+ | 0.3146 | 6200 | 0.0 | - |
307
+ | 0.3172 | 6250 | 0.0 | - |
308
+ | 0.3197 | 6300 | 0.0 | - |
309
+ | 0.3222 | 6350 | 0.0001 | - |
310
+ | 0.3248 | 6400 | 0.0009 | - |
311
+ | 0.3273 | 6450 | 0.0 | - |
312
+ | 0.3298 | 6500 | 0.0 | - |
313
+ | 0.3324 | 6550 | 0.0 | - |
314
+ | 0.3349 | 6600 | 0.0 | - |
315
+ | 0.3375 | 6650 | 0.0 | - |
316
+ | 0.3400 | 6700 | 0.0 | - |
317
+ | 0.3425 | 6750 | 0.0 | - |
318
+ | 0.3451 | 6800 | 0.0 | - |
319
+ | 0.3476 | 6850 | 0.0 | - |
320
+ | 0.3501 | 6900 | 0.0 | - |
321
+ | 0.3527 | 6950 | 0.0 | - |
322
+ | 0.3552 | 7000 | 0.0 | - |
323
+ | 0.3578 | 7050 | 0.0 | - |
324
+ | 0.3603 | 7100 | 0.0536 | - |
325
+ | 0.3628 | 7150 | 0.0 | - |
326
+ | 0.3654 | 7200 | 0.0 | - |
327
+ | 0.3679 | 7250 | 0.0 | - |
328
+ | 0.3704 | 7300 | 0.0 | - |
329
+ | 0.3730 | 7350 | 0.0 | - |
330
+ | 0.3755 | 7400 | 0.0 | - |
331
+ | 0.3781 | 7450 | 0.0 | - |
332
+ | 0.3806 | 7500 | 0.0 | - |
333
+ | 0.3831 | 7550 | 0.0 | - |
334
+ | 0.3857 | 7600 | 0.0 | - |
335
+ | 0.3882 | 7650 | 0.0 | - |
336
+ | 0.3907 | 7700 | 0.0 | - |
337
+ | 0.3933 | 7750 | 0.0019 | - |
338
+ | 0.3958 | 7800 | 0.0 | - |
339
+ | 0.3984 | 7850 | 0.0 | - |
340
+ | 0.4009 | 7900 | 0.0548 | - |
341
+ | 0.4034 | 7950 | 0.0 | - |
342
+ | 0.4060 | 8000 | 0.0053 | - |
343
+ | 0.4085 | 8050 | 0.0 | - |
344
+ | 0.4110 | 8100 | 0.0 | - |
345
+ | 0.4136 | 8150 | 0.0 | - |
346
+ | 0.4161 | 8200 | 0.0 | - |
347
+ | 0.4187 | 8250 | 0.0624 | - |
348
+ | 0.4212 | 8300 | 0.0622 | - |
349
+ | 0.4237 | 8350 | 0.0618 | - |
350
+ | 0.4263 | 8400 | 0.0001 | - |
351
+ | 0.4288 | 8450 | 0.0 | - |
352
+ | 0.4313 | 8500 | 0.0001 | - |
353
+ | 0.4339 | 8550 | 0.0 | - |
354
+ | 0.4364 | 8600 | 0.0 | - |
355
+ | 0.4390 | 8650 | 0.0 | - |
356
+ | 0.4415 | 8700 | 0.0012 | - |
357
+ | 0.4440 | 8750 | 0.0001 | - |
358
+ | 0.4466 | 8800 | 0.0005 | - |
359
+ | 0.4491 | 8850 | 0.0 | - |
360
+ | 0.4516 | 8900 | 0.0 | - |
361
+ | 0.4542 | 8950 | 0.0 | - |
362
+ | 0.4567 | 9000 | 0.0 | - |
363
+ | 0.4593 | 9050 | 0.0 | - |
364
+ | 0.4618 | 9100 | 0.0 | - |
365
+ | 0.4643 | 9150 | 0.0 | - |
366
+ | 0.4669 | 9200 | 0.0 | - |
367
+ | 0.4694 | 9250 | 0.0408 | - |
368
+ | 0.4719 | 9300 | 0.0498 | - |
369
+ | 0.4745 | 9350 | 0.0 | - |
370
+ | 0.4770 | 9400 | 0.0 | - |
371
+ | 0.4795 | 9450 | 0.0017 | - |
372
+ | 0.4821 | 9500 | 0.0 | - |
373
+ | 0.4846 | 9550 | 0.0 | - |
374
+ | 0.4872 | 9600 | 0.0 | - |
375
+ | 0.4897 | 9650 | 0.0 | - |
376
+ | 0.4922 | 9700 | 0.0 | - |
377
+ | 0.4948 | 9750 | 0.0 | - |
378
+ | 0.4973 | 9800 | 0.0589 | - |
379
+ | 0.4998 | 9850 | 0.0 | - |
380
+ | 0.5024 | 9900 | 0.0 | - |
381
+ | 0.5049 | 9950 | 0.0015 | - |
382
+ | 0.5075 | 10000 | 0.0 | - |
383
+ | 0.5100 | 10050 | 0.0 | - |
384
+ | 0.5125 | 10100 | 0.0 | - |
385
+ | 0.5151 | 10150 | 0.0 | - |
386
+ | 0.5176 | 10200 | 0.0 | - |
387
+ | 0.5201 | 10250 | 0.0 | - |
388
+ | 0.5227 | 10300 | 0.0013 | - |
389
+ | 0.5252 | 10350 | 0.0023 | - |
390
+ | 0.5278 | 10400 | 0.0 | - |
391
+ | 0.5303 | 10450 | 0.0 | - |
392
+ | 0.5328 | 10500 | 0.0 | - |
393
+ | 0.5354 | 10550 | 0.0003 | - |
394
+ | 0.5379 | 10600 | 0.0 | - |
395
+ | 0.5404 | 10650 | 0.0 | - |
396
+ | 0.5430 | 10700 | 0.0002 | - |
397
+ | 0.5455 | 10750 | 0.0 | - |
398
+ | 0.5481 | 10800 | 0.0 | - |
399
+ | 0.5506 | 10850 | 0.0005 | - |
400
+ | 0.5531 | 10900 | 0.0 | - |
401
+ | 0.5557 | 10950 | 0.0 | - |
402
+ | 0.5582 | 11000 | 0.0 | - |
403
+ | 0.5607 | 11050 | 0.0 | - |
404
+ | 0.5633 | 11100 | 0.0 | - |
405
+ | 0.5658 | 11150 | 0.0 | - |
406
+ | 0.5684 | 11200 | 0.0 | - |
407
+ | 0.5709 | 11250 | 0.0 | - |
408
+ | 0.5734 | 11300 | 0.0 | - |
409
+ | 0.5760 | 11350 | 0.0008 | - |
410
+ | 0.5785 | 11400 | 0.0 | - |
411
+ | 0.5810 | 11450 | 0.0024 | - |
412
+ | 0.5836 | 11500 | 0.0 | - |
413
+ | 0.5861 | 11550 | 0.0 | - |
414
+ | 0.5887 | 11600 | 0.0 | - |
415
+ | 0.5912 | 11650 | 0.0 | - |
416
+ | 0.5937 | 11700 | 0.001 | - |
417
+ | 0.5963 | 11750 | 0.0 | - |
418
+ | 0.5988 | 11800 | 0.0 | - |
419
+ | 0.6013 | 11850 | 0.0 | - |
420
+ | 0.6039 | 11900 | 0.0527 | - |
421
+ | 0.6064 | 11950 | 0.0021 | - |
422
+ | 0.6090 | 12000 | 0.0 | - |
423
+ | 0.6115 | 12050 | 0.0 | - |
424
+ | 0.6140 | 12100 | 0.0 | - |
425
+ | 0.6166 | 12150 | 0.0 | - |
426
+ | 0.6191 | 12200 | 0.0 | - |
427
+ | 0.6216 | 12250 | 0.0 | - |
428
+ | 0.6242 | 12300 | 0.0 | - |
429
+ | 0.6267 | 12350 | 0.0006 | - |
430
+ | 0.6292 | 12400 | 0.0 | - |
431
+ | 0.6318 | 12450 | 0.0 | - |
432
+ | 0.6343 | 12500 | 0.001 | - |
433
+ | 0.6369 | 12550 | 0.0017 | - |
434
+ | 0.6394 | 12600 | 0.0 | - |
435
+ | 0.6419 | 12650 | 0.0 | - |
436
+ | 0.6445 | 12700 | 0.0 | - |
437
+ | 0.6470 | 12750 | 0.0012 | - |
438
+ | 0.6495 | 12800 | 0.0 | - |
439
+ | 0.6521 | 12850 | 0.0 | - |
440
+ | 0.6546 | 12900 | 0.0 | - |
441
+ | 0.6572 | 12950 | 0.0434 | - |
442
+ | 0.6597 | 13000 | 0.0 | - |
443
+ | 0.6622 | 13050 | 0.0 | - |
444
+ | 0.6648 | 13100 | 0.0003 | - |
445
+ | 0.6673 | 13150 | 0.0 | - |
446
+ | 0.6698 | 13200 | 0.0 | - |
447
+ | 0.6724 | 13250 | 0.0003 | - |
448
+ | 0.6749 | 13300 | 0.0 | - |
449
+ | 0.6775 | 13350 | 0.0 | - |
450
+ | 0.6800 | 13400 | 0.0005 | - |
451
+ | 0.6825 | 13450 | 0.0 | - |
452
+ | 0.6851 | 13500 | 0.0011 | - |
453
+ | 0.6876 | 13550 | 0.0475 | - |
454
+ | 0.6901 | 13600 | 0.0 | - |
455
+ | 0.6927 | 13650 | 0.0007 | - |
456
+ | 0.6952 | 13700 | 0.0 | - |
457
+ | 0.6978 | 13750 | 0.0 | - |
458
+ | 0.7003 | 13800 | 0.0 | - |
459
+ | 0.7028 | 13850 | 0.0 | - |
460
+ | 0.7054 | 13900 | 0.0 | - |
461
+ | 0.7079 | 13950 | 0.0015 | - |
462
+ | 0.7104 | 14000 | 0.0034 | - |
463
+ | 0.7130 | 14050 | 0.0009 | - |
464
+ | 0.7155 | 14100 | 0.0 | - |
465
+ | 0.7181 | 14150 | 0.0009 | - |
466
+ | 0.7206 | 14200 | 0.0 | - |
467
+ | 0.7231 | 14250 | 0.0003 | - |
468
+ | 0.7257 | 14300 | 0.0004 | - |
469
+ | 0.7282 | 14350 | 0.0 | - |
470
+ | 0.7307 | 14400 | 0.0003 | - |
471
+ | 0.7333 | 14450 | 0.0 | - |
472
+ | 0.7358 | 14500 | 0.0 | - |
473
+ | 0.7384 | 14550 | 0.0 | - |
474
+ | 0.7409 | 14600 | 0.0 | - |
475
+ | 0.7434 | 14650 | 0.0 | - |
476
+ | 0.7460 | 14700 | 0.0018 | - |
477
+ | 0.7485 | 14750 | 0.0012 | - |
478
+ | 0.7510 | 14800 | 0.0 | - |
479
+ | 0.7536 | 14850 | 0.0 | - |
480
+ | 0.7561 | 14900 | 0.0013 | - |
481
+ | 0.7587 | 14950 | 0.0 | - |
482
+ | 0.7612 | 15000 | 0.0 | - |
483
+ | 0.7637 | 15050 | 0.0 | - |
484
+ | 0.7663 | 15100 | 0.0 | - |
485
+ | 0.7688 | 15150 | 0.0 | - |
486
+ | 0.7713 | 15200 | 0.0 | - |
487
+ | 0.7739 | 15250 | 0.0 | - |
488
+ | 0.7764 | 15300 | 0.0 | - |
489
+ | 0.7790 | 15350 | 0.0 | - |
490
+ | 0.7815 | 15400 | 0.0 | - |
491
+ | 0.7840 | 15450 | 0.0 | - |
492
+ | 0.7866 | 15500 | 0.0 | - |
493
+ | 0.7891 | 15550 | 0.0 | - |
494
+ | 0.7916 | 15600 | 0.0004 | - |
495
+ | 0.7942 | 15650 | 0.0005 | - |
496
+ | 0.7967 | 15700 | 0.0 | - |
497
+ | 0.7992 | 15750 | 0.0 | - |
498
+ | 0.8018 | 15800 | 0.0 | - |
499
+ | 0.8043 | 15850 | 0.0 | - |
500
+ | 0.8069 | 15900 | 0.0 | - |
501
+ | 0.8094 | 15950 | 0.0555 | - |
502
+ | 0.8119 | 16000 | 0.0 | - |
503
+ | 0.8145 | 16050 | 0.0 | - |
504
+ | 0.8170 | 16100 | 0.0 | - |
505
+ | 0.8195 | 16150 | 0.0 | - |
506
+ | 0.8221 | 16200 | 0.0 | - |
507
+ | 0.8246 | 16250 | 0.0007 | - |
508
+ | 0.8272 | 16300 | 0.0 | - |
509
+ | 0.8297 | 16350 | 0.0 | - |
510
+ | 0.8322 | 16400 | 0.0 | - |
511
+ | 0.8348 | 16450 | 0.0003 | - |
512
+ | 0.8373 | 16500 | 0.0 | - |
513
+ | 0.8398 | 16550 | 0.0012 | - |
514
+ | 0.8424 | 16600 | 0.0 | - |
515
+ | 0.8449 | 16650 | 0.0 | - |
516
+ | 0.8475 | 16700 | 0.0 | - |
517
+ | 0.8500 | 16750 | 0.0 | - |
518
+ | 0.8525 | 16800 | 0.0 | - |
519
+ | 0.8551 | 16850 | 0.0 | - |
520
+ | 0.8576 | 16900 | 0.0007 | - |
521
+ | 0.8601 | 16950 | 0.0 | - |
522
+ | 0.8627 | 17000 | 0.001 | - |
523
+ | 0.8652 | 17050 | 0.0 | - |
524
+ | 0.8678 | 17100 | 0.0 | - |
525
+ | 0.8703 | 17150 | 0.0 | - |
526
+ | 0.8728 | 17200 | 0.0 | - |
527
+ | 0.8754 | 17250 | 0.0 | - |
528
+ | 0.8779 | 17300 | 0.0 | - |
529
+ | 0.8804 | 17350 | 0.0 | - |
530
+ | 0.8830 | 17400 | 0.0007 | - |
531
+ | 0.8855 | 17450 | 0.0 | - |
532
+ | 0.8881 | 17500 | 0.0 | - |
533
+ | 0.8906 | 17550 | 0.0505 | - |
534
+ | 0.8931 | 17600 | 0.0 | - |
535
+ | 0.8957 | 17650 | 0.0 | - |
536
+ | 0.8982 | 17700 | 0.0008 | - |
537
+ | 0.9007 | 17750 | 0.0 | - |
538
+ | 0.9033 | 17800 | 0.0003 | - |
539
+ | 0.9058 | 17850 | 0.0 | - |
540
+ | 0.9084 | 17900 | 0.0 | - |
541
+ | 0.9109 | 17950 | 0.0009 | - |
542
+ | 0.9134 | 18000 | 0.0 | - |
543
+ | 0.9160 | 18050 | 0.0 | - |
544
+ | 0.9185 | 18100 | 0.0 | - |
545
+ | 0.9210 | 18150 | 0.0 | - |
546
+ | 0.9236 | 18200 | 0.0 | - |
547
+ | 0.9261 | 18250 | 0.0 | - |
548
+ | 0.9287 | 18300 | 0.0 | - |
549
+ | 0.9312 | 18350 | 0.0008 | - |
550
+ | 0.9337 | 18400 | 0.0 | - |
551
+ | 0.9363 | 18450 | 0.0 | - |
552
+ | 0.9388 | 18500 | 0.0 | - |
553
+ | 0.9413 | 18550 | 0.0 | - |
554
+ | 0.9439 | 18600 | 0.0 | - |
555
+ | 0.9464 | 18650 | 0.0 | - |
556
+ | 0.9489 | 18700 | 0.0 | - |
557
+ | 0.9515 | 18750 | 0.0 | - |
558
+ | 0.9540 | 18800 | 0.0 | - |
559
+ | 0.9566 | 18850 | 0.0 | - |
560
+ | 0.9591 | 18900 | 0.0 | - |
561
+ | 0.9616 | 18950 | 0.0 | - |
562
+ | 0.9642 | 19000 | 0.0 | - |
563
+ | 0.9667 | 19050 | 0.0 | - |
564
+ | 0.9692 | 19100 | 0.0 | - |
565
+ | 0.9718 | 19150 | 0.0 | - |
566
+ | 0.9743 | 19200 | 0.0 | - |
567
+ | 0.9769 | 19250 | 0.0 | - |
568
+ | 0.9794 | 19300 | 0.0005 | - |
569
+ | 0.9819 | 19350 | 0.0 | - |
570
+ | 0.9845 | 19400 | 0.0 | - |
571
+ | 0.9870 | 19450 | 0.0 | - |
572
+ | 0.9895 | 19500 | 0.0 | - |
573
+ | 0.9921 | 19550 | 0.0011 | - |
574
+ | 0.9946 | 19600 | 0.0 | - |
575
+ | 0.9972 | 19650 | 0.0 | - |
576
+ | 0.9997 | 19700 | 0.0 | - |
577
+
578
+ ### Framework Versions
579
+ - Python: 3.10.12
580
+ - SetFit: 1.0.3
581
+ - Sentence Transformers: 2.2.2
582
+ - spaCy: 3.6.1
583
+ - Transformers: 4.35.2
584
+ - PyTorch: 2.1.0+cu121
585
+ - Datasets: 2.16.1
586
+ - Tokenizers: 0.15.1
587
+
588
+ ## Citation
589
+
590
+ ### BibTeX
591
+ ```bibtex
592
+ @article{https://doi.org/10.48550/arxiv.2209.11055,
593
+ doi = {10.48550/ARXIV.2209.11055},
594
+ url = {https://arxiv.org/abs/2209.11055},
595
+ author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
596
+ keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
597
+ title = {Efficient Few-Shot Learning Without Prompts},
598
+ publisher = {arXiv},
599
+ year = {2022},
600
+ copyright = {Creative Commons Attribution 4.0 International}
601
+ }
602
+ ```
603
+
604
+ <!--
605
+ ## Glossary
606
+
607
+ *Clearly define terms in order to be accessible across audiences.*
608
+ -->
609
+
610
+ <!--
611
+ ## Model Card Authors
612
+
613
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
614
+ -->
615
+
616
+ <!--
617
+ ## Model Card Contact
618
+
619
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
620
+ -->
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/.cache/torch/sentence_transformers/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": "4.35.2",
23
+ "vocab_size": 30527
24
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.0.0",
4
+ "transformers": "4.7.0",
5
+ "pytorch": "1.9.0+cu102"
6
+ }
7
+ }
config_setfit.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "span_context": 0,
3
+ "labels": [
4
+ "no aspect",
5
+ "aspect"
6
+ ],
7
+ "normalize_embeddings": false,
8
+ "spacy_model": "en_core_web_lg"
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd3890482c8271b0eee7f6d41b191faab6b7ae6d7d99102ccd886f8b1db8658d
3
+ size 437967672
model_head.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f59d809144c1b7f843932eb57bffc928bb61af809d510d9fdd5eb9107bf8b379
3
+ size 6975
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": true,
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": true,
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