Add SetFit model
Browse files- 1_Pooling/config.json +7 -0
- README.md +458 -0
- config.json +24 -0
- config_sentence_transformers.json +7 -0
- config_setfit.json +4 -0
- model.safetensors +3 -0
- model_head.pkl +3 -0
- modules.json +20 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +72 -0
- 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
ADDED
@@ -0,0 +1,458 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: setfit
|
3 |
+
tags:
|
4 |
+
- setfit
|
5 |
+
- sentence-transformers
|
6 |
+
- text-classification
|
7 |
+
- generated_from_setfit_trainer
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
widget:
|
11 |
+
- text: "Rly tragedy in MP: Some live to recount horror: \x89ÛÏWhen I saw coaches\
|
12 |
+
\ of my train plunging into water I called my daughters and said t..."
|
13 |
+
- text: You must be annihilated!
|
14 |
+
- text: 'Severe Thunderstorms and Flash Flooding Possible in the Mid-South and Midwest
|
15 |
+
http://t.co/uAhIcWpIh4 #WEATHER #ENVIRONMENT #CLIMATE #NATURE'
|
16 |
+
- text: 'everyone''s wonder who will win and I''m over here wondering are those grapes
|
17 |
+
real ?????? #BB17'
|
18 |
+
- text: i swea it feels like im about to explode ??
|
19 |
+
pipeline_tag: text-classification
|
20 |
+
inference: true
|
21 |
+
base_model: sentence-transformers/all-mpnet-base-v2
|
22 |
+
model-index:
|
23 |
+
- name: SetFit with sentence-transformers/all-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: 0.9203152364273205
|
35 |
+
name: Accuracy
|
36 |
+
---
|
37 |
+
|
38 |
+
# SetFit with sentence-transformers/all-mpnet-base-v2
|
39 |
+
|
40 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. 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.
|
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 |
+
## Model Details
|
48 |
+
|
49 |
+
### Model Description
|
50 |
+
- **Model Type:** SetFit
|
51 |
+
- **Sentence Transformer body:** [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2)
|
52 |
+
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
53 |
+
- **Maximum Sequence Length:** 384 tokens
|
54 |
+
- **Number of Classes:** 2 classes
|
55 |
+
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
56 |
+
<!-- - **Language:** Unknown -->
|
57 |
+
<!-- - **License:** Unknown -->
|
58 |
+
|
59 |
+
### Model Sources
|
60 |
+
|
61 |
+
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
|
62 |
+
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
63 |
+
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
64 |
+
|
65 |
+
### Model Labels
|
66 |
+
| Label | Examples |
|
67 |
+
|:------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
68 |
+
| 0 | <ul><li>'To fight bioterrorism sir.'</li><li>'85V-265V 10W LED Warm White Light Motion Sensor Outdoor Flood Light PIR Lamp AUC http://t.co/NJVPXzMj5V http://t.co/Ijd7WzV5t9'</li><li>'Photo: referencereference: xekstrin: I THOUGHT THE NOSTRILS WERE EYES AND I ALMOST CRIED FROM FEAR partake... http://t.co/O7yYjLuKfJ'</li></ul> |
|
69 |
+
| 1 | <ul><li>'Police officer wounded suspect dead after exchanging shots: RICHMOND Va. (AP) \x89ÛÓ A Richmond police officer wa... http://t.co/Y0qQS2L7bS'</li><li>"There's a weird siren going off here...I hope Hunterston isn't in the process of blowing itself to smithereens..."</li><li>'Iranian warship points weapon at American helicopter... http://t.co/cgFZk8Ha1R'</li></ul> |
|
70 |
+
|
71 |
+
## Evaluation
|
72 |
+
|
73 |
+
### Metrics
|
74 |
+
| Label | Accuracy |
|
75 |
+
|:--------|:---------|
|
76 |
+
| **all** | 0.9203 |
|
77 |
+
|
78 |
+
## Uses
|
79 |
+
|
80 |
+
### Direct Use for Inference
|
81 |
+
|
82 |
+
First install the SetFit library:
|
83 |
+
|
84 |
+
```bash
|
85 |
+
pip install setfit
|
86 |
+
```
|
87 |
+
|
88 |
+
Then you can load this model and run inference.
|
89 |
+
|
90 |
+
```python
|
91 |
+
from setfit import SetFitModel
|
92 |
+
|
93 |
+
# Download from the 🤗 Hub
|
94 |
+
model = SetFitModel.from_pretrained("pEpOo/catastrophy8")
|
95 |
+
# Run inference
|
96 |
+
preds = model("You must be annihilated!")
|
97 |
+
```
|
98 |
+
|
99 |
+
<!--
|
100 |
+
### Downstream Use
|
101 |
+
|
102 |
+
*List how someone could finetune this model on their own dataset.*
|
103 |
+
-->
|
104 |
+
|
105 |
+
<!--
|
106 |
+
### Out-of-Scope Use
|
107 |
+
|
108 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
109 |
+
-->
|
110 |
+
|
111 |
+
<!--
|
112 |
+
## Bias, Risks and Limitations
|
113 |
+
|
114 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
115 |
+
-->
|
116 |
+
|
117 |
+
<!--
|
118 |
+
### Recommendations
|
119 |
+
|
120 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
121 |
+
-->
|
122 |
+
|
123 |
+
## Training Details
|
124 |
+
|
125 |
+
### Training Set Metrics
|
126 |
+
| Training set | Min | Median | Max |
|
127 |
+
|:-------------|:----|:--------|:----|
|
128 |
+
| Word count | 1 | 14.5506 | 54 |
|
129 |
+
|
130 |
+
| Label | Training Sample Count |
|
131 |
+
|:------|:----------------------|
|
132 |
+
| 0 | 438 |
|
133 |
+
| 1 | 323 |
|
134 |
+
|
135 |
+
### Training Hyperparameters
|
136 |
+
- batch_size: (20, 20)
|
137 |
+
- num_epochs: (1, 1)
|
138 |
+
- max_steps: -1
|
139 |
+
- sampling_strategy: oversampling
|
140 |
+
- num_iterations: 20
|
141 |
+
- body_learning_rate: (2e-05, 2e-05)
|
142 |
+
- head_learning_rate: 2e-05
|
143 |
+
- loss: CosineSimilarityLoss
|
144 |
+
- distance_metric: cosine_distance
|
145 |
+
- margin: 0.25
|
146 |
+
- end_to_end: False
|
147 |
+
- use_amp: False
|
148 |
+
- warmup_proportion: 0.1
|
149 |
+
- seed: 42
|
150 |
+
- eval_max_steps: -1
|
151 |
+
- load_best_model_at_end: False
|
152 |
+
|
153 |
+
### Training Results
|
154 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
155 |
+
|:------:|:-----:|:-------------:|:---------------:|
|
156 |
+
| 0.0001 | 1 | 0.3847 | - |
|
157 |
+
| 0.0044 | 50 | 0.3738 | - |
|
158 |
+
| 0.0088 | 100 | 0.2274 | - |
|
159 |
+
| 0.0131 | 150 | 0.2747 | - |
|
160 |
+
| 0.0175 | 200 | 0.2251 | - |
|
161 |
+
| 0.0219 | 250 | 0.2562 | - |
|
162 |
+
| 0.0263 | 300 | 0.2623 | - |
|
163 |
+
| 0.0307 | 350 | 0.1904 | - |
|
164 |
+
| 0.0350 | 400 | 0.2314 | - |
|
165 |
+
| 0.0394 | 450 | 0.1669 | - |
|
166 |
+
| 0.0438 | 500 | 0.1135 | - |
|
167 |
+
| 0.0482 | 550 | 0.1489 | - |
|
168 |
+
| 0.0525 | 600 | 0.1907 | - |
|
169 |
+
| 0.0569 | 650 | 0.1728 | - |
|
170 |
+
| 0.0613 | 700 | 0.125 | - |
|
171 |
+
| 0.0657 | 750 | 0.109 | - |
|
172 |
+
| 0.0701 | 800 | 0.0968 | - |
|
173 |
+
| 0.0744 | 850 | 0.2101 | - |
|
174 |
+
| 0.0788 | 900 | 0.1974 | - |
|
175 |
+
| 0.0832 | 950 | 0.1986 | - |
|
176 |
+
| 0.0876 | 1000 | 0.0747 | - |
|
177 |
+
| 0.0920 | 1050 | 0.1117 | - |
|
178 |
+
| 0.0963 | 1100 | 0.1092 | - |
|
179 |
+
| 0.1007 | 1150 | 0.1582 | - |
|
180 |
+
| 0.1051 | 1200 | 0.1243 | - |
|
181 |
+
| 0.1095 | 1250 | 0.2873 | - |
|
182 |
+
| 0.1139 | 1300 | 0.2415 | - |
|
183 |
+
| 0.1182 | 1350 | 0.1264 | - |
|
184 |
+
| 0.1226 | 1400 | 0.127 | - |
|
185 |
+
| 0.1270 | 1450 | 0.1308 | - |
|
186 |
+
| 0.1314 | 1500 | 0.0669 | - |
|
187 |
+
| 0.1358 | 1550 | 0.1218 | - |
|
188 |
+
| 0.1401 | 1600 | 0.114 | - |
|
189 |
+
| 0.1445 | 1650 | 0.0612 | - |
|
190 |
+
| 0.1489 | 1700 | 0.0527 | - |
|
191 |
+
| 0.1533 | 1750 | 0.1421 | - |
|
192 |
+
| 0.1576 | 1800 | 0.0048 | - |
|
193 |
+
| 0.1620 | 1850 | 0.0141 | - |
|
194 |
+
| 0.1664 | 1900 | 0.0557 | - |
|
195 |
+
| 0.1708 | 1950 | 0.0206 | - |
|
196 |
+
| 0.1752 | 2000 | 0.1171 | - |
|
197 |
+
| 0.1795 | 2050 | 0.0968 | - |
|
198 |
+
| 0.1839 | 2100 | 0.0243 | - |
|
199 |
+
| 0.1883 | 2150 | 0.0233 | - |
|
200 |
+
| 0.1927 | 2200 | 0.0738 | - |
|
201 |
+
| 0.1971 | 2250 | 0.0071 | - |
|
202 |
+
| 0.2014 | 2300 | 0.0353 | - |
|
203 |
+
| 0.2058 | 2350 | 0.0602 | - |
|
204 |
+
| 0.2102 | 2400 | 0.003 | - |
|
205 |
+
| 0.2146 | 2450 | 0.0625 | - |
|
206 |
+
| 0.2190 | 2500 | 0.0173 | - |
|
207 |
+
| 0.2233 | 2550 | 0.1017 | - |
|
208 |
+
| 0.2277 | 2600 | 0.0582 | - |
|
209 |
+
| 0.2321 | 2650 | 0.0437 | - |
|
210 |
+
| 0.2365 | 2700 | 0.104 | - |
|
211 |
+
| 0.2408 | 2750 | 0.0156 | - |
|
212 |
+
| 0.2452 | 2800 | 0.0034 | - |
|
213 |
+
| 0.2496 | 2850 | 0.0343 | - |
|
214 |
+
| 0.2540 | 2900 | 0.1106 | - |
|
215 |
+
| 0.2584 | 2950 | 0.001 | - |
|
216 |
+
| 0.2627 | 3000 | 0.004 | - |
|
217 |
+
| 0.2671 | 3050 | 0.0074 | - |
|
218 |
+
| 0.2715 | 3100 | 0.0849 | - |
|
219 |
+
| 0.2759 | 3150 | 0.0009 | - |
|
220 |
+
| 0.2803 | 3200 | 0.0379 | - |
|
221 |
+
| 0.2846 | 3250 | 0.0109 | - |
|
222 |
+
| 0.2890 | 3300 | 0.0019 | - |
|
223 |
+
| 0.2934 | 3350 | 0.0154 | - |
|
224 |
+
| 0.2978 | 3400 | 0.0017 | - |
|
225 |
+
| 0.3022 | 3450 | 0.0003 | - |
|
226 |
+
| 0.3065 | 3500 | 0.0002 | - |
|
227 |
+
| 0.3109 | 3550 | 0.0025 | - |
|
228 |
+
| 0.3153 | 3600 | 0.0123 | - |
|
229 |
+
| 0.3197 | 3650 | 0.0007 | - |
|
230 |
+
| 0.3240 | 3700 | 0.0534 | - |
|
231 |
+
| 0.3284 | 3750 | 0.0004 | - |
|
232 |
+
| 0.3328 | 3800 | 0.0084 | - |
|
233 |
+
| 0.3372 | 3850 | 0.0088 | - |
|
234 |
+
| 0.3416 | 3900 | 0.0201 | - |
|
235 |
+
| 0.3459 | 3950 | 0.0002 | - |
|
236 |
+
| 0.3503 | 4000 | 0.0102 | - |
|
237 |
+
| 0.3547 | 4050 | 0.0043 | - |
|
238 |
+
| 0.3591 | 4100 | 0.0124 | - |
|
239 |
+
| 0.3635 | 4150 | 0.0845 | - |
|
240 |
+
| 0.3678 | 4200 | 0.0002 | - |
|
241 |
+
| 0.3722 | 4250 | 0.0014 | - |
|
242 |
+
| 0.3766 | 4300 | 0.1131 | - |
|
243 |
+
| 0.3810 | 4350 | 0.0612 | - |
|
244 |
+
| 0.3854 | 4400 | 0.0577 | - |
|
245 |
+
| 0.3897 | 4450 | 0.0235 | - |
|
246 |
+
| 0.3941 | 4500 | 0.0156 | - |
|
247 |
+
| 0.3985 | 4550 | 0.0078 | - |
|
248 |
+
| 0.4029 | 4600 | 0.0356 | - |
|
249 |
+
| 0.4073 | 4650 | 0.0595 | - |
|
250 |
+
| 0.4116 | 4700 | 0.0001 | - |
|
251 |
+
| 0.4160 | 4750 | 0.0018 | - |
|
252 |
+
| 0.4204 | 4800 | 0.0013 | - |
|
253 |
+
| 0.4248 | 4850 | 0.0008 | - |
|
254 |
+
| 0.4291 | 4900 | 0.0832 | - |
|
255 |
+
| 0.4335 | 4950 | 0.0083 | - |
|
256 |
+
| 0.4379 | 5000 | 0.0007 | - |
|
257 |
+
| 0.4423 | 5050 | 0.0417 | - |
|
258 |
+
| 0.4467 | 5100 | 0.0001 | - |
|
259 |
+
| 0.4510 | 5150 | 0.0218 | - |
|
260 |
+
| 0.4554 | 5200 | 0.0001 | - |
|
261 |
+
| 0.4598 | 5250 | 0.0012 | - |
|
262 |
+
| 0.4642 | 5300 | 0.0002 | - |
|
263 |
+
| 0.4686 | 5350 | 0.0006 | - |
|
264 |
+
| 0.4729 | 5400 | 0.0223 | - |
|
265 |
+
| 0.4773 | 5450 | 0.0612 | - |
|
266 |
+
| 0.4817 | 5500 | 0.0004 | - |
|
267 |
+
| 0.4861 | 5550 | 0.0 | - |
|
268 |
+
| 0.4905 | 5600 | 0.0007 | - |
|
269 |
+
| 0.4948 | 5650 | 0.0007 | - |
|
270 |
+
| 0.4992 | 5700 | 0.0116 | - |
|
271 |
+
| 0.5036 | 5750 | 0.0262 | - |
|
272 |
+
| 0.5080 | 5800 | 0.0336 | - |
|
273 |
+
| 0.5123 | 5850 | 0.026 | - |
|
274 |
+
| 0.5167 | 5900 | 0.0004 | - |
|
275 |
+
| 0.5211 | 5950 | 0.0001 | - |
|
276 |
+
| 0.5255 | 6000 | 0.0001 | - |
|
277 |
+
| 0.5299 | 6050 | 0.0001 | - |
|
278 |
+
| 0.5342 | 6100 | 0.0029 | - |
|
279 |
+
| 0.5386 | 6150 | 0.0001 | - |
|
280 |
+
| 0.5430 | 6200 | 0.0699 | - |
|
281 |
+
| 0.5474 | 6250 | 0.0262 | - |
|
282 |
+
| 0.5518 | 6300 | 0.0269 | - |
|
283 |
+
| 0.5561 | 6350 | 0.0002 | - |
|
284 |
+
| 0.5605 | 6400 | 0.0666 | - |
|
285 |
+
| 0.5649 | 6450 | 0.0209 | - |
|
286 |
+
| 0.5693 | 6500 | 0.0003 | - |
|
287 |
+
| 0.5737 | 6550 | 0.0001 | - |
|
288 |
+
| 0.5780 | 6600 | 0.0115 | - |
|
289 |
+
| 0.5824 | 6650 | 0.0003 | - |
|
290 |
+
| 0.5868 | 6700 | 0.0001 | - |
|
291 |
+
| 0.5912 | 6750 | 0.0056 | - |
|
292 |
+
| 0.5956 | 6800 | 0.0603 | - |
|
293 |
+
| 0.5999 | 6850 | 0.0002 | - |
|
294 |
+
| 0.6043 | 6900 | 0.0003 | - |
|
295 |
+
| 0.6087 | 6950 | 0.0092 | - |
|
296 |
+
| 0.6131 | 7000 | 0.0562 | - |
|
297 |
+
| 0.6174 | 7050 | 0.0408 | - |
|
298 |
+
| 0.6218 | 7100 | 0.0001 | - |
|
299 |
+
| 0.6262 | 7150 | 0.0035 | - |
|
300 |
+
| 0.6306 | 7200 | 0.0337 | - |
|
301 |
+
| 0.6350 | 7250 | 0.0024 | - |
|
302 |
+
| 0.6393 | 7300 | 0.0005 | - |
|
303 |
+
| 0.6437 | 7350 | 0.0001 | - |
|
304 |
+
| 0.6481 | 7400 | 0.0 | - |
|
305 |
+
| 0.6525 | 7450 | 0.0001 | - |
|
306 |
+
| 0.6569 | 7500 | 0.0002 | - |
|
307 |
+
| 0.6612 | 7550 | 0.0004 | - |
|
308 |
+
| 0.6656 | 7600 | 0.0125 | - |
|
309 |
+
| 0.6700 | 7650 | 0.0005 | - |
|
310 |
+
| 0.6744 | 7700 | 0.0157 | - |
|
311 |
+
| 0.6788 | 7750 | 0.0055 | - |
|
312 |
+
| 0.6831 | 7800 | 0.0 | - |
|
313 |
+
| 0.6875 | 7850 | 0.0053 | - |
|
314 |
+
| 0.6919 | 7900 | 0.0 | - |
|
315 |
+
| 0.6963 | 7950 | 0.0002 | - |
|
316 |
+
| 0.7006 | 8000 | 0.0002 | - |
|
317 |
+
| 0.7050 | 8050 | 0.0001 | - |
|
318 |
+
| 0.7094 | 8100 | 0.0001 | - |
|
319 |
+
| 0.7138 | 8150 | 0.0001 | - |
|
320 |
+
| 0.7182 | 8200 | 0.0007 | - |
|
321 |
+
| 0.7225 | 8250 | 0.0002 | - |
|
322 |
+
| 0.7269 | 8300 | 0.0001 | - |
|
323 |
+
| 0.7313 | 8350 | 0.0 | - |
|
324 |
+
| 0.7357 | 8400 | 0.0156 | - |
|
325 |
+
| 0.7401 | 8450 | 0.0098 | - |
|
326 |
+
| 0.7444 | 8500 | 0.0 | - |
|
327 |
+
| 0.7488 | 8550 | 0.0001 | - |
|
328 |
+
| 0.7532 | 8600 | 0.0042 | - |
|
329 |
+
| 0.7576 | 8650 | 0.0 | - |
|
330 |
+
| 0.7620 | 8700 | 0.0 | - |
|
331 |
+
| 0.7663 | 8750 | 0.0056 | - |
|
332 |
+
| 0.7707 | 8800 | 0.0 | - |
|
333 |
+
| 0.7751 | 8850 | 0.0 | - |
|
334 |
+
| 0.7795 | 8900 | 0.013 | - |
|
335 |
+
| 0.7839 | 8950 | 0.0 | - |
|
336 |
+
| 0.7882 | 9000 | 0.0001 | - |
|
337 |
+
| 0.7926 | 9050 | 0.0 | - |
|
338 |
+
| 0.7970 | 9100 | 0.0 | - |
|
339 |
+
| 0.8014 | 9150 | 0.0 | - |
|
340 |
+
| 0.8057 | 9200 | 0.0 | - |
|
341 |
+
| 0.8101 | 9250 | 0.0 | - |
|
342 |
+
| 0.8145 | 9300 | 0.0007 | - |
|
343 |
+
| 0.8189 | 9350 | 0.0 | - |
|
344 |
+
| 0.8233 | 9400 | 0.0002 | - |
|
345 |
+
| 0.8276 | 9450 | 0.0 | - |
|
346 |
+
| 0.8320 | 9500 | 0.0 | - |
|
347 |
+
| 0.8364 | 9550 | 0.0089 | - |
|
348 |
+
| 0.8408 | 9600 | 0.0001 | - |
|
349 |
+
| 0.8452 | 9650 | 0.0 | - |
|
350 |
+
| 0.8495 | 9700 | 0.0 | - |
|
351 |
+
| 0.8539 | 9750 | 0.0 | - |
|
352 |
+
| 0.8583 | 9800 | 0.0565 | - |
|
353 |
+
| 0.8627 | 9850 | 0.0161 | - |
|
354 |
+
| 0.8671 | 9900 | 0.0 | - |
|
355 |
+
| 0.8714 | 9950 | 0.0246 | - |
|
356 |
+
| 0.8758 | 10000 | 0.0 | - |
|
357 |
+
| 0.8802 | 10050 | 0.0 | - |
|
358 |
+
| 0.8846 | 10100 | 0.012 | - |
|
359 |
+
| 0.8889 | 10150 | 0.0 | - |
|
360 |
+
| 0.8933 | 10200 | 0.0 | - |
|
361 |
+
| 0.8977 | 10250 | 0.0 | - |
|
362 |
+
| 0.9021 | 10300 | 0.0 | - |
|
363 |
+
| 0.9065 | 10350 | 0.0 | - |
|
364 |
+
| 0.9108 | 10400 | 0.0 | - |
|
365 |
+
| 0.9152 | 10450 | 0.0 | - |
|
366 |
+
| 0.9196 | 10500 | 0.0 | - |
|
367 |
+
| 0.9240 | 10550 | 0.0023 | - |
|
368 |
+
| 0.9284 | 10600 | 0.0 | - |
|
369 |
+
| 0.9327 | 10650 | 0.0006 | - |
|
370 |
+
| 0.9371 | 10700 | 0.0 | - |
|
371 |
+
| 0.9415 | 10750 | 0.0 | - |
|
372 |
+
| 0.9459 | 10800 | 0.0 | - |
|
373 |
+
| 0.9503 | 10850 | 0.0 | - |
|
374 |
+
| 0.9546 | 10900 | 0.0 | - |
|
375 |
+
| 0.9590 | 10950 | 0.0243 | - |
|
376 |
+
| 0.9634 | 11000 | 0.0107 | - |
|
377 |
+
| 0.9678 | 11050 | 0.0001 | - |
|
378 |
+
| 0.9721 | 11100 | 0.0 | - |
|
379 |
+
| 0.9765 | 11150 | 0.0 | - |
|
380 |
+
| 0.9809 | 11200 | 0.0274 | - |
|
381 |
+
| 0.9853 | 11250 | 0.0 | - |
|
382 |
+
| 0.9897 | 11300 | 0.0 | - |
|
383 |
+
| 0.9940 | 11350 | 0.0 | - |
|
384 |
+
| 0.9984 | 11400 | 0.0 | - |
|
385 |
+
| 0.0007 | 1 | 0.2021 | - |
|
386 |
+
| 0.0329 | 50 | 0.1003 | - |
|
387 |
+
| 0.0657 | 100 | 0.2282 | - |
|
388 |
+
| 0.0986 | 150 | 0.0507 | - |
|
389 |
+
| 0.1314 | 200 | 0.046 | - |
|
390 |
+
| 0.1643 | 250 | 0.0001 | - |
|
391 |
+
| 0.1971 | 300 | 0.0495 | - |
|
392 |
+
| 0.2300 | 350 | 0.0031 | - |
|
393 |
+
| 0.2628 | 400 | 0.0004 | - |
|
394 |
+
| 0.2957 | 450 | 0.0002 | - |
|
395 |
+
| 0.3285 | 500 | 0.0 | - |
|
396 |
+
| 0.3614 | 550 | 0.0 | - |
|
397 |
+
| 0.3942 | 600 | 0.0 | - |
|
398 |
+
| 0.4271 | 650 | 0.0001 | - |
|
399 |
+
| 0.4599 | 700 | 0.0 | - |
|
400 |
+
| 0.4928 | 750 | 0.0 | - |
|
401 |
+
| 0.5256 | 800 | 0.0 | - |
|
402 |
+
| 0.5585 | 850 | 0.0 | - |
|
403 |
+
| 0.5913 | 900 | 0.0001 | - |
|
404 |
+
| 0.6242 | 950 | 0.0 | - |
|
405 |
+
| 0.6570 | 1000 | 0.0001 | - |
|
406 |
+
| 0.6899 | 1050 | 0.0 | - |
|
407 |
+
| 0.7227 | 1100 | 0.0 | - |
|
408 |
+
| 0.7556 | 1150 | 0.0 | - |
|
409 |
+
| 0.7884 | 1200 | 0.0 | - |
|
410 |
+
| 0.8213 | 1250 | 0.0 | - |
|
411 |
+
| 0.8541 | 1300 | 0.0 | - |
|
412 |
+
| 0.8870 | 1350 | 0.0 | - |
|
413 |
+
| 0.9198 | 1400 | 0.0 | - |
|
414 |
+
| 0.9527 | 1450 | 0.0001 | - |
|
415 |
+
| 0.9855 | 1500 | 0.0 | - |
|
416 |
+
|
417 |
+
### Framework Versions
|
418 |
+
- Python: 3.10.12
|
419 |
+
- SetFit: 1.0.1
|
420 |
+
- Sentence Transformers: 2.2.2
|
421 |
+
- Transformers: 4.35.2
|
422 |
+
- PyTorch: 2.1.0+cu121
|
423 |
+
- Datasets: 2.15.0
|
424 |
+
- Tokenizers: 0.15.0
|
425 |
+
|
426 |
+
## Citation
|
427 |
+
|
428 |
+
### BibTeX
|
429 |
+
```bibtex
|
430 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
431 |
+
doi = {10.48550/ARXIV.2209.11055},
|
432 |
+
url = {https://arxiv.org/abs/2209.11055},
|
433 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
434 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
435 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
436 |
+
publisher = {arXiv},
|
437 |
+
year = {2022},
|
438 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
439 |
+
}
|
440 |
+
```
|
441 |
+
|
442 |
+
<!--
|
443 |
+
## Glossary
|
444 |
+
|
445 |
+
*Clearly define terms in order to be accessible across audiences.*
|
446 |
+
-->
|
447 |
+
|
448 |
+
<!--
|
449 |
+
## Model Card Authors
|
450 |
+
|
451 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
452 |
+
-->
|
453 |
+
|
454 |
+
<!--
|
455 |
+
## Model Card Contact
|
456 |
+
|
457 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
458 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/root/.cache/torch/sentence_transformers/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": "4.35.2",
|
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": "4.6.1",
|
5 |
+
"pytorch": "1.8.1"
|
6 |
+
}
|
7 |
+
}
|
config_setfit.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"labels": null,
|
3 |
+
"normalize_embeddings": false
|
4 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0a46dcfb6be02899ea086ac43102c2c5bd24f455a97a08edb65c67548ebf476
|
3 |
+
size 437967672
|
model_head.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72d19dfb91af07be37c7c350746ff9d74a50b61213e6a4a029580e1d4c140824
|
3 |
+
size 6991
|
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": 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 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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
|
|