Add SetFit model
Browse files- 1_Pooling/config.json +10 -0
- README.md +411 -0
- config.json +24 -0
- config_sentence_transformers.json +9 -0
- config_setfit.json +40 -0
- model.safetensors +3 -0
- model_head.pkl +3 -0
- modules.json +14 -0
- sentence_bert_config.json +4 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +66 -0
- 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 +1,411 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: setfit
|
3 |
+
tags:
|
4 |
+
- setfit
|
5 |
+
- sentence-transformers
|
6 |
+
- text-classification
|
7 |
+
- generated_from_setfit_trainer
|
8 |
+
base_model: sentence-transformers/paraphrase-mpnet-base-v2
|
9 |
+
metrics:
|
10 |
+
- accuracy
|
11 |
+
widget:
|
12 |
+
- text: travel book a train ticket
|
13 |
+
- text: how much is the average house
|
14 |
+
- text: do i need a jacket
|
15 |
+
- text: i like the songs of yeshudas please play it
|
16 |
+
- text: tell me the current time
|
17 |
+
pipeline_tag: text-classification
|
18 |
+
inference: true
|
19 |
+
model-index:
|
20 |
+
- name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2
|
21 |
+
results:
|
22 |
+
- task:
|
23 |
+
type: text-classification
|
24 |
+
name: Text Classification
|
25 |
+
dataset:
|
26 |
+
name: Unknown
|
27 |
+
type: unknown
|
28 |
+
split: test
|
29 |
+
metrics:
|
30 |
+
- type: accuracy
|
31 |
+
value: 0.7743480574773816
|
32 |
+
name: Accuracy
|
33 |
+
---
|
34 |
+
|
35 |
+
# SetFit with sentence-transformers/paraphrase-mpnet-base-v2
|
36 |
+
|
37 |
+
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.
|
38 |
+
|
39 |
+
The model has been trained using an efficient few-shot learning technique that involves:
|
40 |
+
|
41 |
+
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
|
42 |
+
2. Training a classification head with features from the fine-tuned Sentence Transformer.
|
43 |
+
|
44 |
+
## Model Details
|
45 |
+
|
46 |
+
### Model Description
|
47 |
+
- **Model Type:** SetFit
|
48 |
+
- **Sentence Transformer body:** [sentence-transformers/paraphrase-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-mpnet-base-v2)
|
49 |
+
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
|
50 |
+
- **Maximum Sequence Length:** 512 tokens
|
51 |
+
- **Number of Classes:** 35 classes
|
52 |
+
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
|
53 |
+
<!-- - **Language:** Unknown -->
|
54 |
+
<!-- - **License:** Unknown -->
|
55 |
+
|
56 |
+
### Model Sources
|
57 |
+
|
58 |
+
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
|
59 |
+
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
|
60 |
+
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
|
61 |
+
|
62 |
+
### Model Labels
|
63 |
+
| Label | Examples |
|
64 |
+
|:-------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
65 |
+
| alarm_query | <ul><li>'do i have any alarms set for six am tomorrow'</li><li>'what is the wake up time for my alarm i have set for the flight this weekend'</li><li>'please tell me what alarms are on'</li></ul> |
|
66 |
+
| alarm_set | <ul><li>'set an alarm for six thirty am'</li><li>'add an alarm for tomorrow morning at six am'</li><li>'wake me up at five am'</li></ul> |
|
67 |
+
| audio_volume_mute | <ul><li>'can you please stop speaking'</li><li>'turn off sound'</li><li>'shut down the sound'</li></ul> |
|
68 |
+
| calendar_query | <ul><li>'how long will my lunch meeting be on tuesday'</li><li>'what time is my doctor appointment on march thirty first'</li><li>'what days do i have booked'</li></ul> |
|
69 |
+
| calendar_remove | <ul><li>'clear everything off my calendar for the rest of the year'</li><li>'please clear my calendar'</li><li>'remove from my calendar meeting at nine am'</li></ul> |
|
70 |
+
| calendar_set | <ul><li>'new event'</li><li>'remind me of the event in my calendar'</li><li>"mark april twenty as my brother's birthday"</li></ul> |
|
71 |
+
| cooking_recipe | <ul><li>'tell me the recipe of'</li><li>'how is rice prepared'</li><li>'what ingredient can be used instead of saffron'</li></ul> |
|
72 |
+
| datetime_query | <ul><li>'what is the time in canada now'</li><li>"what's the time in australia"</li><li>'display the local time of london at this moment'</li></ul> |
|
73 |
+
| email_query | <ul><li>'do i have any unread emails'</li><li>'what about new mail'</li><li>'olly do i have any new emails'</li></ul> |
|
74 |
+
| email_sendemail | <ul><li>'dictate email'</li><li>'reply an email to jason that i will not come tonight'</li><li>'please send an email to cassy who is there on my family and friend list'</li></ul> |
|
75 |
+
| general_quirky | <ul><li>'where was will ferrell seen last night'</li><li>'do you think i should go to the theater today'</li><li>'what is the best chocolate chip cookies recipe'</li></ul> |
|
76 |
+
| iot_coffee | <ul><li>'i need a drink'</li><li>'please activate my coffee pot for me'</li><li>'prepare a cup of coffee for me'</li></ul> |
|
77 |
+
| iot_hue_lightchange | <ul><li>'please make the lights natural'</li><li>'make the room light blue'</li><li>'hey olly chance the current light settings'</li></ul> |
|
78 |
+
| iot_hue_lightoff | <ul><li>'siri please turn the lights off in the bathroom'</li><li>'turn my bedroom lights off'</li><li>'no lights in the kitchen'</li></ul> |
|
79 |
+
| lists_createoradd | <ul><li>'add business contacts to contact list'</li><li>'please create a new list for me'</li><li>"i want to make this week's shopping list"</li></ul> |
|
80 |
+
| lists_query | <ul><li>'give me all available lists'</li><li>'give me the details on purchase order'</li><li>'find the list'</li></ul> |
|
81 |
+
| lists_remove | <ul><li>'replace'</li><li>"delete my to do's for this week"</li><li>'get rid of tax list from nineteen ninety'</li></ul> |
|
82 |
+
| music_likeness | <ul><li>'store opinion on song'</li><li>'are there any upcoming concerts by'</li><li>'enter song suggestion'</li></ul> |
|
83 |
+
| music_query | <ul><li>'is the song by shakira'</li><li>'which film the music comes from what is the name of the music'</li><li>'which song is this one'</li></ul> |
|
84 |
+
| news_query | <ul><li>'news articles on a particular subject'</li><li>'get me match highlights'</li><li>'show me the latest news from the guardian'</li></ul> |
|
85 |
+
| play_audiobook | <ul><li>'continue the last chapter of the audio book i was listening to'</li><li>'open davinci code audiobook'</li><li>'resume the playback of a child called it'</li></ul> |
|
86 |
+
| play_game | <ul><li>'bring up papa pear saga'</li><li>'play ping pong'</li><li>'play racing'</li></ul> |
|
87 |
+
| play_music | <ul><li>'play mf doom anything'</li><li>'play only all music released between the year one thousand nine hundred and ninety and two thousand'</li><li>'nobody knows'</li></ul> |
|
88 |
+
| play_podcasts | <ul><li>'play all order of the green hand from previous week'</li><li>'i want to see the next podcast available'</li><li>"search for podcasts that cover men's issues"</li></ul> |
|
89 |
+
| play_radio | <ul><li>'can you turn on the radio'</li><li>'play country radio'</li><li>'tune to classic hits'</li></ul> |
|
90 |
+
| qa_currency | <ul><li>'let me know about the exchange rate of rupee to dirham'</li><li>'how much is one dollar in pounds'</li><li>'what is the most current exchange rate in china'</li></ul> |
|
91 |
+
| qa_definition | <ul><li>'define elaborate'</li><li>'look up the definition of blunder'</li><li>'give details of rock sand'</li></ul> |
|
92 |
+
| qa_factoid | <ul><li>'where are the rocky mountains'</li><li>'what is the population of new york'</li><li>'where is new zealand located on a map'</li></ul> |
|
93 |
+
| recommendation_events | <ul><li>'are there any fun events in la today'</li><li>"what's happening around me"</li><li>'are there any crafts fairs happening in this area'</li></ul> |
|
94 |
+
| recommendation_locations | <ul><li>'what is the nearest pizza shop'</li><li>'please look up local restaurants that are open now'</li><li>'tell me what clothing stores are within five miles of me'</li></ul> |
|
95 |
+
| social_post | <ul><li>"tweet at united airlines i'm angry you lost my bags"</li><li>'send a funny message to all of my friends'</li><li>'tweet my current location'</li></ul> |
|
96 |
+
| takeaway_query | <ul><li>'could you please confirm if paradise does takeaway'</li><li>"i've canceled the order placed at mcd did it go through"</li><li>"please find out of charley's steakhouse delivers"</li></ul> |
|
97 |
+
| transport_query | <ul><li>'directions please'</li><li>'what time does the train to place leave'</li><li>'look up the map to stores near me'</li></ul> |
|
98 |
+
| transport_ticket | <ul><li>'find me a train ticket to boston'</li><li>'can you please book train tickets for two for this friday'</li><li>'order a train ticket to boston'</li></ul> |
|
99 |
+
| weather_query | <ul><li>'will i need to shovel my driveway this morning'</li><li>'does the weather call for rain saturday'</li><li>'is there any rain in the forecast for the next week'</li></ul> |
|
100 |
+
|
101 |
+
## Evaluation
|
102 |
+
|
103 |
+
### Metrics
|
104 |
+
| Label | Accuracy |
|
105 |
+
|:--------|:---------|
|
106 |
+
| **all** | 0.7743 |
|
107 |
+
|
108 |
+
## Uses
|
109 |
+
|
110 |
+
### Direct Use for Inference
|
111 |
+
|
112 |
+
First install the SetFit library:
|
113 |
+
|
114 |
+
```bash
|
115 |
+
pip install setfit
|
116 |
+
```
|
117 |
+
|
118 |
+
Then you can load this model and run inference.
|
119 |
+
|
120 |
+
```python
|
121 |
+
from setfit import SetFitModel
|
122 |
+
|
123 |
+
# Download from the 🤗 Hub
|
124 |
+
model = SetFitModel.from_pretrained("aisuko/st-mpnet-v2-amazon-mi")
|
125 |
+
# Run inference
|
126 |
+
preds = model("do i need a jacket")
|
127 |
+
```
|
128 |
+
|
129 |
+
<!--
|
130 |
+
### Downstream Use
|
131 |
+
|
132 |
+
*List how someone could finetune this model on their own dataset.*
|
133 |
+
-->
|
134 |
+
|
135 |
+
<!--
|
136 |
+
### Out-of-Scope Use
|
137 |
+
|
138 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
139 |
+
-->
|
140 |
+
|
141 |
+
<!--
|
142 |
+
## Bias, Risks and Limitations
|
143 |
+
|
144 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
145 |
+
-->
|
146 |
+
|
147 |
+
<!--
|
148 |
+
### Recommendations
|
149 |
+
|
150 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
151 |
+
-->
|
152 |
+
|
153 |
+
## Training Details
|
154 |
+
|
155 |
+
### Training Set Metrics
|
156 |
+
| Training set | Min | Median | Max |
|
157 |
+
|:-------------|:----|:-------|:----|
|
158 |
+
| Word count | 1 | 6.7114 | 19 |
|
159 |
+
|
160 |
+
| Label | Training Sample Count |
|
161 |
+
|:-------------------------|:----------------------|
|
162 |
+
| alarm_query | 10 |
|
163 |
+
| alarm_set | 10 |
|
164 |
+
| audio_volume_mute | 10 |
|
165 |
+
| calendar_query | 10 |
|
166 |
+
| calendar_remove | 10 |
|
167 |
+
| calendar_set | 10 |
|
168 |
+
| cooking_recipe | 10 |
|
169 |
+
| datetime_query | 10 |
|
170 |
+
| email_query | 10 |
|
171 |
+
| email_sendemail | 10 |
|
172 |
+
| general_quirky | 10 |
|
173 |
+
| iot_coffee | 10 |
|
174 |
+
| iot_hue_lightchange | 10 |
|
175 |
+
| iot_hue_lightoff | 10 |
|
176 |
+
| lists_createoradd | 10 |
|
177 |
+
| lists_query | 10 |
|
178 |
+
| lists_remove | 10 |
|
179 |
+
| music_likeness | 10 |
|
180 |
+
| music_query | 10 |
|
181 |
+
| news_query | 10 |
|
182 |
+
| play_audiobook | 10 |
|
183 |
+
| play_game | 10 |
|
184 |
+
| play_music | 10 |
|
185 |
+
| play_podcasts | 10 |
|
186 |
+
| play_radio | 10 |
|
187 |
+
| qa_currency | 10 |
|
188 |
+
| qa_definition | 10 |
|
189 |
+
| qa_factoid | 10 |
|
190 |
+
| recommendation_events | 10 |
|
191 |
+
| recommendation_locations | 10 |
|
192 |
+
| social_post | 10 |
|
193 |
+
| takeaway_query | 10 |
|
194 |
+
| transport_query | 10 |
|
195 |
+
| transport_ticket | 10 |
|
196 |
+
| weather_query | 10 |
|
197 |
+
|
198 |
+
### Training Hyperparameters
|
199 |
+
- batch_size: (16, 16)
|
200 |
+
- num_epochs: (1, 1)
|
201 |
+
- max_steps: -1
|
202 |
+
- sampling_strategy: oversampling
|
203 |
+
- body_learning_rate: (2e-05, 1e-05)
|
204 |
+
- head_learning_rate: 0.01
|
205 |
+
- loss: CosineSimilarityLoss
|
206 |
+
- distance_metric: cosine_distance
|
207 |
+
- margin: 0.25
|
208 |
+
- end_to_end: False
|
209 |
+
- use_amp: False
|
210 |
+
- warmup_proportion: 0.1
|
211 |
+
- seed: 42
|
212 |
+
- eval_max_steps: -1
|
213 |
+
- load_best_model_at_end: True
|
214 |
+
|
215 |
+
### Training Results
|
216 |
+
| Epoch | Step | Training Loss | Validation Loss |
|
217 |
+
|:-------:|:--------:|:-------------:|:---------------:|
|
218 |
+
| 0.0001 | 1 | 0.1814 | - |
|
219 |
+
| 0.0067 | 50 | 0.1542 | - |
|
220 |
+
| 0.0134 | 100 | 0.0953 | - |
|
221 |
+
| 0.0202 | 150 | 0.0991 | - |
|
222 |
+
| 0.0269 | 200 | 0.0717 | - |
|
223 |
+
| 0.0336 | 250 | 0.0653 | - |
|
224 |
+
| 0.0403 | 300 | 0.0412 | - |
|
225 |
+
| 0.0471 | 350 | 0.0534 | - |
|
226 |
+
| 0.0538 | 400 | 0.013 | - |
|
227 |
+
| 0.0605 | 450 | 0.0567 | - |
|
228 |
+
| 0.0672 | 500 | 0.0235 | - |
|
229 |
+
| 0.0739 | 550 | 0.0086 | - |
|
230 |
+
| 0.0807 | 600 | 0.0086 | - |
|
231 |
+
| 0.0874 | 650 | 0.0786 | - |
|
232 |
+
| 0.0941 | 700 | 0.0092 | - |
|
233 |
+
| 0.1008 | 750 | 0.0081 | - |
|
234 |
+
| 0.1076 | 800 | 0.0196 | - |
|
235 |
+
| 0.1143 | 850 | 0.0138 | - |
|
236 |
+
| 0.1210 | 900 | 0.0081 | - |
|
237 |
+
| 0.1277 | 950 | 0.0295 | - |
|
238 |
+
| 0.1344 | 1000 | 0.0074 | - |
|
239 |
+
| 0.1412 | 1050 | 0.0025 | - |
|
240 |
+
| 0.1479 | 1100 | 0.0036 | - |
|
241 |
+
| 0.1546 | 1150 | 0.0021 | - |
|
242 |
+
| 0.1613 | 1200 | 0.0168 | - |
|
243 |
+
| 0.1681 | 1250 | 0.0024 | - |
|
244 |
+
| 0.1748 | 1300 | 0.0039 | - |
|
245 |
+
| 0.1815 | 1350 | 0.0155 | - |
|
246 |
+
| 0.1882 | 1400 | 0.0057 | - |
|
247 |
+
| 0.1949 | 1450 | 0.0027 | - |
|
248 |
+
| 0.2017 | 1500 | 0.0018 | - |
|
249 |
+
| 0.2084 | 1550 | 0.0012 | - |
|
250 |
+
| 0.2151 | 1600 | 0.0032 | - |
|
251 |
+
| 0.2218 | 1650 | 0.0017 | - |
|
252 |
+
| 0.2286 | 1700 | 0.0012 | - |
|
253 |
+
| 0.2353 | 1750 | 0.002 | - |
|
254 |
+
| 0.2420 | 1800 | 0.0025 | - |
|
255 |
+
| 0.2487 | 1850 | 0.0014 | - |
|
256 |
+
| 0.2554 | 1900 | 0.0033 | - |
|
257 |
+
| 0.2622 | 1950 | 0.0007 | - |
|
258 |
+
| 0.2689 | 2000 | 0.0006 | - |
|
259 |
+
| 0.2756 | 2050 | 0.001 | - |
|
260 |
+
| 0.2823 | 2100 | 0.001 | - |
|
261 |
+
| 0.2891 | 2150 | 0.0007 | - |
|
262 |
+
| 0.2958 | 2200 | 0.0011 | - |
|
263 |
+
| 0.3025 | 2250 | 0.0009 | - |
|
264 |
+
| 0.3092 | 2300 | 0.0006 | - |
|
265 |
+
| 0.3159 | 2350 | 0.001 | - |
|
266 |
+
| 0.3227 | 2400 | 0.0005 | - |
|
267 |
+
| 0.3294 | 2450 | 0.0012 | - |
|
268 |
+
| 0.3361 | 2500 | 0.0005 | - |
|
269 |
+
| 0.3428 | 2550 | 0.0007 | - |
|
270 |
+
| 0.3496 | 2600 | 0.0018 | - |
|
271 |
+
| 0.3563 | 2650 | 0.0008 | - |
|
272 |
+
| 0.3630 | 2700 | 0.0009 | - |
|
273 |
+
| 0.3697 | 2750 | 0.0007 | - |
|
274 |
+
| 0.3764 | 2800 | 0.0013 | - |
|
275 |
+
| 0.3832 | 2850 | 0.0004 | - |
|
276 |
+
| 0.3899 | 2900 | 0.0005 | - |
|
277 |
+
| 0.3966 | 2950 | 0.0005 | - |
|
278 |
+
| 0.4033 | 3000 | 0.0006 | - |
|
279 |
+
| 0.4101 | 3050 | 0.0005 | - |
|
280 |
+
| 0.4168 | 3100 | 0.0004 | - |
|
281 |
+
| 0.4235 | 3150 | 0.0007 | - |
|
282 |
+
| 0.4302 | 3200 | 0.0009 | - |
|
283 |
+
| 0.4369 | 3250 | 0.0007 | - |
|
284 |
+
| 0.4437 | 3300 | 0.0007 | - |
|
285 |
+
| 0.4504 | 3350 | 0.0004 | - |
|
286 |
+
| 0.4571 | 3400 | 0.0004 | - |
|
287 |
+
| 0.4638 | 3450 | 0.0009 | - |
|
288 |
+
| 0.4706 | 3500 | 0.0006 | - |
|
289 |
+
| 0.4773 | 3550 | 0.0006 | - |
|
290 |
+
| 0.4840 | 3600 | 0.0005 | - |
|
291 |
+
| 0.4907 | 3650 | 0.0005 | - |
|
292 |
+
| 0.4974 | 3700 | 0.0003 | - |
|
293 |
+
| 0.5042 | 3750 | 0.0004 | - |
|
294 |
+
| 0.5109 | 3800 | 0.0004 | - |
|
295 |
+
| 0.5176 | 3850 | 0.0005 | - |
|
296 |
+
| 0.5243 | 3900 | 0.0007 | - |
|
297 |
+
| 0.5311 | 3950 | 0.0005 | - |
|
298 |
+
| 0.5378 | 4000 | 0.0006 | - |
|
299 |
+
| 0.5445 | 4050 | 0.0004 | - |
|
300 |
+
| 0.5512 | 4100 | 0.0006 | - |
|
301 |
+
| 0.5579 | 4150 | 0.0005 | - |
|
302 |
+
| 0.5647 | 4200 | 0.0004 | - |
|
303 |
+
| 0.5714 | 4250 | 0.0003 | - |
|
304 |
+
| 0.5781 | 4300 | 0.0003 | - |
|
305 |
+
| 0.5848 | 4350 | 0.0005 | - |
|
306 |
+
| 0.5916 | 4400 | 0.0002 | - |
|
307 |
+
| 0.5983 | 4450 | 0.0006 | - |
|
308 |
+
| 0.6050 | 4500 | 0.0004 | - |
|
309 |
+
| 0.6117 | 4550 | 0.0005 | - |
|
310 |
+
| 0.6184 | 4600 | 0.0003 | - |
|
311 |
+
| 0.6252 | 4650 | 0.0005 | - |
|
312 |
+
| 0.6319 | 4700 | 0.0007 | - |
|
313 |
+
| 0.6386 | 4750 | 0.0003 | - |
|
314 |
+
| 0.6453 | 4800 | 0.0004 | - |
|
315 |
+
| 0.6521 | 4850 | 0.0004 | - |
|
316 |
+
| 0.6588 | 4900 | 0.0004 | - |
|
317 |
+
| 0.6655 | 4950 | 0.0003 | - |
|
318 |
+
| 0.6722 | 5000 | 0.0003 | - |
|
319 |
+
| 0.6789 | 5050 | 0.0004 | - |
|
320 |
+
| 0.6857 | 5100 | 0.0003 | - |
|
321 |
+
| 0.6924 | 5150 | 0.0005 | - |
|
322 |
+
| 0.6991 | 5200 | 0.0002 | - |
|
323 |
+
| 0.7058 | 5250 | 0.0004 | - |
|
324 |
+
| 0.7126 | 5300 | 0.0003 | - |
|
325 |
+
| 0.7193 | 5350 | 0.0007 | - |
|
326 |
+
| 0.7260 | 5400 | 0.0002 | - |
|
327 |
+
| 0.7327 | 5450 | 0.0002 | - |
|
328 |
+
| 0.7394 | 5500 | 0.0005 | - |
|
329 |
+
| 0.7462 | 5550 | 0.0003 | - |
|
330 |
+
| 0.7529 | 5600 | 0.0003 | - |
|
331 |
+
| 0.7596 | 5650 | 0.0003 | - |
|
332 |
+
| 0.7663 | 5700 | 0.0004 | - |
|
333 |
+
| 0.7731 | 5750 | 0.0004 | - |
|
334 |
+
| 0.7798 | 5800 | 0.0004 | - |
|
335 |
+
| 0.7865 | 5850 | 0.0003 | - |
|
336 |
+
| 0.7932 | 5900 | 0.0003 | - |
|
337 |
+
| 0.7999 | 5950 | 0.0004 | - |
|
338 |
+
| 0.8067 | 6000 | 0.0004 | - |
|
339 |
+
| 0.8134 | 6050 | 0.0004 | - |
|
340 |
+
| 0.8201 | 6100 | 0.0003 | - |
|
341 |
+
| 0.8268 | 6150 | 0.0002 | - |
|
342 |
+
| 0.8336 | 6200 | 0.0005 | - |
|
343 |
+
| 0.8403 | 6250 | 0.0003 | - |
|
344 |
+
| 0.8470 | 6300 | 0.0003 | - |
|
345 |
+
| 0.8537 | 6350 | 0.0002 | - |
|
346 |
+
| 0.8604 | 6400 | 0.0003 | - |
|
347 |
+
| 0.8672 | 6450 | 0.0004 | - |
|
348 |
+
| 0.8739 | 6500 | 0.0002 | - |
|
349 |
+
| 0.8806 | 6550 | 0.0003 | - |
|
350 |
+
| 0.8873 | 6600 | 0.0003 | - |
|
351 |
+
| 0.8941 | 6650 | 0.0002 | - |
|
352 |
+
| 0.9008 | 6700 | 0.0002 | - |
|
353 |
+
| 0.9075 | 6750 | 0.0002 | - |
|
354 |
+
| 0.9142 | 6800 | 0.0002 | - |
|
355 |
+
| 0.9209 | 6850 | 0.0003 | - |
|
356 |
+
| 0.9277 | 6900 | 0.0002 | - |
|
357 |
+
| 0.9344 | 6950 | 0.0002 | - |
|
358 |
+
| 0.9411 | 7000 | 0.0002 | - |
|
359 |
+
| 0.9478 | 7050 | 0.0002 | - |
|
360 |
+
| 0.9546 | 7100 | 0.0002 | - |
|
361 |
+
| 0.9613 | 7150 | 0.0003 | - |
|
362 |
+
| 0.9680 | 7200 | 0.0002 | - |
|
363 |
+
| 0.9747 | 7250 | 0.0003 | - |
|
364 |
+
| 0.9814 | 7300 | 0.0002 | - |
|
365 |
+
| 0.9882 | 7350 | 0.0003 | - |
|
366 |
+
| 0.9949 | 7400 | 0.0003 | - |
|
367 |
+
| **1.0** | **7438** | **-** | **0.0755** |
|
368 |
+
|
369 |
+
* The bold row denotes the saved checkpoint.
|
370 |
+
### Framework Versions
|
371 |
+
- Python: 3.10.13
|
372 |
+
- SetFit: 1.0.3
|
373 |
+
- Sentence Transformers: 2.7.0
|
374 |
+
- Transformers: 4.39.3
|
375 |
+
- PyTorch: 2.1.2
|
376 |
+
- Datasets: 2.18.0
|
377 |
+
- Tokenizers: 0.15.2
|
378 |
+
|
379 |
+
## Citation
|
380 |
+
|
381 |
+
### BibTeX
|
382 |
+
```bibtex
|
383 |
+
@article{https://doi.org/10.48550/arxiv.2209.11055,
|
384 |
+
doi = {10.48550/ARXIV.2209.11055},
|
385 |
+
url = {https://arxiv.org/abs/2209.11055},
|
386 |
+
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
|
387 |
+
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
|
388 |
+
title = {Efficient Few-Shot Learning Without Prompts},
|
389 |
+
publisher = {arXiv},
|
390 |
+
year = {2022},
|
391 |
+
copyright = {Creative Commons Attribution 4.0 International}
|
392 |
+
}
|
393 |
+
```
|
394 |
+
|
395 |
+
<!--
|
396 |
+
## Glossary
|
397 |
+
|
398 |
+
*Clearly define terms in order to be accessible across audiences.*
|
399 |
+
-->
|
400 |
+
|
401 |
+
<!--
|
402 |
+
## Model Card Authors
|
403 |
+
|
404 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
405 |
+
-->
|
406 |
+
|
407 |
+
<!--
|
408 |
+
## Model Card Contact
|
409 |
+
|
410 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
411 |
+
-->
|
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "checkpoints/step_7438",
|
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 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"labels": [
|
3 |
+
"alarm_query",
|
4 |
+
"alarm_set",
|
5 |
+
"audio_volume_mute",
|
6 |
+
"calendar_query",
|
7 |
+
"calendar_remove",
|
8 |
+
"calendar_set",
|
9 |
+
"cooking_recipe",
|
10 |
+
"datetime_query",
|
11 |
+
"email_query",
|
12 |
+
"email_sendemail",
|
13 |
+
"general_quirky",
|
14 |
+
"iot_coffee",
|
15 |
+
"iot_hue_lightchange",
|
16 |
+
"iot_hue_lightoff",
|
17 |
+
"lists_createoradd",
|
18 |
+
"lists_query",
|
19 |
+
"lists_remove",
|
20 |
+
"music_likeness",
|
21 |
+
"music_query",
|
22 |
+
"news_query",
|
23 |
+
"play_audiobook",
|
24 |
+
"play_game",
|
25 |
+
"play_music",
|
26 |
+
"play_podcasts",
|
27 |
+
"play_radio",
|
28 |
+
"qa_currency",
|
29 |
+
"qa_definition",
|
30 |
+
"qa_factoid",
|
31 |
+
"recommendation_events",
|
32 |
+
"recommendation_locations",
|
33 |
+
"social_post",
|
34 |
+
"takeaway_query",
|
35 |
+
"transport_query",
|
36 |
+
"transport_ticket",
|
37 |
+
"weather_query"
|
38 |
+
],
|
39 |
+
"normalize_embeddings": false
|
40 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b482e150831172528ea843eb4d7551be91ddd15f31e94cffb99ae7739b537f0b
|
3 |
+
size 437967672
|
model_head.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e5fd14bfcf391c3d5c0c7e2c6a3d76901b1146b5cdd3a4095e899784c463db5
|
3 |
+
size 219519
|
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 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"max_length": 512,
|
52 |
+
"model_max_length": 512,
|
53 |
+
"never_split": null,
|
54 |
+
"pad_to_multiple_of": null,
|
55 |
+
"pad_token": "<pad>",
|
56 |
+
"pad_token_type_id": 0,
|
57 |
+
"padding_side": "right",
|
58 |
+
"sep_token": "</s>",
|
59 |
+
"stride": 0,
|
60 |
+
"strip_accents": null,
|
61 |
+
"tokenize_chinese_chars": true,
|
62 |
+
"tokenizer_class": "MPNetTokenizer",
|
63 |
+
"truncation_side": "right",
|
64 |
+
"truncation_strategy": "longest_first",
|
65 |
+
"unk_token": "[UNK]"
|
66 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|