Varun1010 commited on
Commit
bddd49b
1 Parent(s): ba8aed0

Add SetFit model

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 384,
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 +1,418 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: Tiong Bahru Plaza, DDC-L2-5, AHU-L2-03 trip alarm
12
+ - text: 'Tiong Bahru Plaza, DDC L4-1, PAU-L4-03 supply air temperature (Units: °C).2'
13
+ - text: Tiong Bahru Plaza, DDC-L20, AHU 20-1 VSD CONTROL
14
+ - text: 'Tiong Bahru Plaza, VAV 19-7, Discharge Air Flow (Units: m3/h)'
15
+ - text: Tiong Bahru Plaza, DDC-L2-5, PAU-L2-02 VSD control
16
+ pipeline_tag: text-classification
17
+ inference: true
18
+ base_model: sentence-transformers/paraphrase-MiniLM-L3-v2
19
+ model-index:
20
+ - name: SetFit with sentence-transformers/paraphrase-MiniLM-L3-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: 0.8019925280199253
32
+ name: Accuracy
33
+ ---
34
+
35
+ # SetFit with sentence-transformers/paraphrase-MiniLM-L3-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-MiniLM-L3-v2](https://huggingface.co/sentence-transformers/paraphrase-MiniLM-L3-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-MiniLM-L3-v2](https://huggingface.co/sentence-transformers/paraphrase-MiniLM-L3-v2)
49
+ - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
50
+ - **Maximum Sequence Length:** 128 tokens
51
+ - **Number of Classes:** 42 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
+ | 13 | <ul><li>'Tiong Bahru Plaza, DDC L14-1, AHU 14-1 TRIP ALARM'</li><li>'Tiong Bahru Plaza, DDC-L1-1, AHU-L1-01 trip alarm'</li><li>'Tiong Bahru Plaza, DDC-B1-5, AHU-B1-2-Trip'</li></ul> |
66
+ | 4 | <ul><li>'Tiong Bahru Plaza, DDC L12, AHU 10-1 FLOW'</li><li>'Tiong Bahru Plaza, DDC-L6, AHU 4-1 Flow'</li><li>'Tiong Bahru Plaza, DDC L14-1, AHU 12-1 Flow (Units: Pa)'</li></ul> |
67
+ | 8 | <ul><li>'Tiong Bahru Plaza, DDC-L6, AHU 5-3 OCT (Units: °C)'</li><li>'Tiong Bahru Plaza, DDC-L2-8, PAU-L2-03 supply air temperature (Units: °C)'</li><li>'Tiong Bahru Plaza, DDC-L20, AHU 20-1 OCT (Units: °C)'</li></ul> |
68
+ | 16 | <ul><li>'Tiong Bahru Plaza, VAV 19-14, Discharge Air Temperature (Units: °C)'</li><li>'Tiong Bahru Plaza, VAV 19-2, Discharge Air Temperature (Units: °C)'</li><li>'Tiong Bahru Plaza, VAV 19-17, Discharge Air Temperature (Units: °C)'</li></ul> |
69
+ | 2 | <ul><li>'Tiong Bahru Plaza, DDC-9-1, AHU 7-1 FAD Feedback'</li><li>'Tiong Bahru Plaza, DDC-L1-1, AHU-L1-01 FAD feedback'</li><li>'Tiong Bahru Plaza, DDC L12, AHU 10-1 FAD Feedback'</li></ul> |
70
+ | 9 | <ul><li>'Tiong Bahru Plaza, DDC-L3-2, AHU-6-2A VSD feedback'</li><li>'Tiong Bahru Plaza, DDC-L1-5, AHU-L3-04A VSD feedback'</li><li>'Tiong Bahru Plaza, DDC-L1-5, PAU-L1-06 VSD feedback'</li></ul> |
71
+ | 6 | <ul><li>'Tiong Bahru Plaza, DDC-L2-5, PAU-L2-04 modulating valve feedback'</li><li>'Tiong Bahru Plaza, DDC-L1-3, AHU-L2-02 modulating valve feedback'</li><li>'Tiong Bahru Plaza, DDC-L2-2, AHU-L2-05 modulating valve feedback'</li></ul> |
72
+ | 21 | <ul><li>'Tiong Bahru Plaza, VAV 19-6, Active Setpoint (Units: °C).1'</li><li>'Tiong Bahru Plaza, VAV 19-12, Active Setpoint (Units: °C)'</li><li>'Tiong Bahru Plaza, VAV 18-17, Active Setpoint (Units: °C)'</li></ul> |
73
+ | 10 | <ul><li>'Tiong Bahru Plaza, DDC-L1-4, PAU-L1-05 Start/Stop Control'</li><li>'Tiong Bahru Plaza, DDC L14-1, AHU12-1 Start/Stop'</li><li>'Tiong Bahru Plaza, DDC-9-1, AHU 8-1 Start/Stop Control'</li></ul> |
74
+ | 35 | <ul><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Header CWS Temperature'</li><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Chiller 4 CWS Temperature'</li><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Chiller 4 CHWS Temperature'</li></ul> |
75
+ | 7 | <ul><li>'Tiong Bahru Plaza, DDC-L3-3, AHU-L3-1 returm air temperature (Units: °C)'</li><li>'Tiong Bahru Plaza, DDC-B1-6, AHU-B1-1 Return Temperature (Units: °C)'</li><li>'Tiong Bahru Plaza, DDC-L2-5, AHU-L2-03 returm air temperature (Units: °C)'</li></ul> |
76
+ | 1 | <ul><li>'Tiong Bahru Plaza, DDC B1-4, PAU-B1-1 Static pressure'</li><li>'Tiong Bahru Plaza, DDC-L3-2, PAU-L3-01 static pressure (Units: Pa)'</li><li>'Tiong Bahru Plaza, DDC-L1-4, PAU-L1-05 Static pressure (Units: Pa)'</li></ul> |
77
+ | 26 | <ul><li>'Tiong Bahru Plaza, MB-T2-1, Active Power kW'</li><li>'Tiong Bahru Plaza, MB-1-S2, Active Power kW'</li><li>'Tiong Bahru Plaza, MB-4-S1, Active Power kW'</li></ul> |
78
+ | 34 | <ul><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Chiller 4 CWR Temperature'</li><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Chiller 3 CHWR Temperature'</li><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Chiller 4 CHWR Temperature'</li></ul> |
79
+ | 18 | <ul><li>'Tiong Bahru Plaza, DDC_L4-3, Outdoor humidity (Units: %)'</li><li>'Tiong Bahru Plaza, DDC_L4-3, Outdoor humidity (Units: %).1'</li><li>'Tiong Bahru Plaza, DDC_L4-3, Outdoor humidity (Units: %).2'</li></ul> |
80
+ | 0 | <ul><li>'Tiong Bahru Plaza, DDC-L20, Co2 Level 18'</li><li>'Tiong Bahru Plaza, DDC L14-1, AHU 13-1 CO2 Reading (Units: ppm).1'</li><li>'Tiong Bahru Plaza, DDC-L1-5, AHU-L3-04A CO2 sensor reading (Units: ppm)'</li></ul> |
81
+ | 17 | <ul><li>'Tiong Bahru Plaza, DDC-L1-1, PAU-L1-01 switch mode'</li><li>'Tiong Bahru Plaza, DDC B1-3, Pau-B1-02-Switch Mode'</li><li>'Tiong Bahru Plaza, DDC-L2-5, PAU-L2-04 switch mode'</li></ul> |
82
+ | 14 | <ul><li>'Tiong Bahru Plaza, VAV 19-7, Space Temperature (Units: °C)'</li><li>'Tiong Bahru Plaza, VAV 19-12, Space Temperature (Units: °C)'</li><li>'Tiong Bahru Plaza, VAV 19-5, Space Temperature (Units: °C)'</li></ul> |
83
+ | 11 | <ul><li>'Tiong Bahru Plaza, DDC-L1-1, AHU-L1-01 on/off status'</li><li>'Tiong Bahru Plaza, DDC L14-1, AHU 15-1 ON/OFF STATUS'</li><li>'Tiong Bahru Plaza, DDC-9-1, AHU 8-1 On/Off Status'</li></ul> |
84
+ | 41 | <ul><li>'Tiong Bahru Plaza, VAV 19-14, Air Valve Position (Units: %)'</li><li>'Tiong Bahru Plaza, VAV 19-6, Air Valve Position (Units: %).1'</li><li>'Tiong Bahru Plaza, VAV 19-21, Air Valve Position (Units: %)'</li></ul> |
85
+ | 5 | <ul><li>'Tiong Bahru Plaza, DDC-L1-4, PAU-L1-05 valve control (Units: %)'</li><li>'Tiong Bahru Plaza, DDC L12, AHU 10-1 VALVE CONTROL (Units: %)'</li><li>'Tiong Bahru Plaza, DDC-L1-3, AHU-L2-02 valve control (Units: %)'</li></ul> |
86
+ | 20 | <ul><li>'Tiong Bahru Plaza, VAV 19-19, Air Flow Setpoint Active (Units: m3/h)'</li><li>'Tiong Bahru Plaza, VAV-19-A, Air Flow Setpoint Active (Units: m3/h)'</li><li>'Tiong Bahru Plaza, VAV 19-4, Air Flow Setpoint Active (Units: m3/h)'</li></ul> |
87
+ | 37 | <ul><li>'Tiong Bahru Plaza, UC800_101001_Chiller_1, Evaporator Refrigerant Pressure - Circuit 1 (Units: Pa)'</li><li>'Tiong Bahru Plaza, UC800_3, Evaporator Refrigerant Pressure - Circuit 1 (Units: Pa)'</li><li>'Tiong Bahru Plaza, UC800_102002_Chiller_2, Evaporator Refrigerant Pressure - Circuit 1 (Units: Pa)'</li></ul> |
88
+ | 31 | <ul><li>'Tiong Bahru Plaza, UC800_102004, Cond Water Flow'</li><li>'Tiong Bahru Plaza, UC800_102004, Condenser Water Flow'</li><li>'Tiong Bahru Plaza, UC800_102005, Condenser Water Flow'</li></ul> |
89
+ | 3 | <ul><li>'Tiong Bahru Plaza, DDC-L1-5, AHU-L3-04A FAD control'</li><li>'Tiong Bahru Plaza, DDC-L6, AHU 4-1 FAD Control'</li><li>'Tiong Bahru Plaza, DDC-L17, AHU 16-1 FAD Control (Units: %)'</li></ul> |
90
+ | 15 | <ul><li>'Tiong Bahru Plaza, VAV 19-2, Discharge Air Flow (Units: m3/h)'</li><li>'Tiong Bahru Plaza, VAV 19-16, Discharge Air Flow (Units: m3/h)'</li><li>'Tiong Bahru Plaza, VAV 19-12, Discharge Air Flow (Units: m3/h)'</li></ul> |
91
+ | 36 | <ul><li>'Tiong Bahru Plaza, UC800_102002_Chiller_2, Entering Condenser Water (Units: °C)'</li><li>'Tiong Bahru Plaza, UC800_101001_Chiller_1, Entering Condenser Water (Units: °C)'</li><li>'Tiong Bahru Plaza, UC800_3, Entering Condenser Water (Units: °C)'</li></ul> |
92
+ | 12 | <ul><li>'Tiong Bahru Plaza, DDC-L20, PAHU TR-1(R-1) SMOKE ALARM'</li><li>'Tiong Bahru Plaza, DDC-L1-4, PAU-L1-03 smoke alarm'</li><li>'Tiong Bahru Plaza, DDC-L1-3, AHU-L1-02 smoke alarm'</li></ul> |
93
+ | 30 | <ul><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Head CWR Temp'</li><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Header CWR Temperature'</li><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Header CWR Temp'</li></ul> |
94
+ | 19 | <ul><li>'Tiong Bahru Plaza, DDC_L4-3, Outdoor temperature (Units: °C).2'</li><li>'Tiong Bahru Plaza, DDC_L4-3, Outdoor temperature (Units: °C)'</li><li>'Tiong Bahru Plaza, DDC_L4-3, Outdoor temperature (Units: °C).1'</li></ul> |
95
+ | 24 | <ul><li>'Tiong Bahru Plaza, DDC-L3-3, AHU-L3-1 VSD Const'</li><li>'Tiong Bahru Plaza, DDC L2-4, AHU L2-04 VSD control'</li><li>'Tiong Bahru Plaza, DDC-L6, AHU 4-1 VSD Control (Units: %)'</li></ul> |
96
+ | 28 | <ul><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Header CHWR Temperature'</li><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Header CHWR Temperature'</li><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Header CHWR Temp'</li></ul> |
97
+ | 27 | <ul><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Chiller 4 CHW Flowrate'</li><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Header CHW Flowrate'</li><li>'Tiong Bahru Plaza, UC800_102002_Chiller_2, Chilled Water Flow'</li></ul> |
98
+ | 33 | <ul><li>'Tiong Bahru Plaza, UC800_3, Condenser Saturated Refrigerant Temperature Circuit 1 (Units: °C)'</li><li>'Tiong Bahru Plaza, UC800_102002_Chiller_2, Condenser Saturated Refrigerant Temperature Circuit 1 (Units: °C)'</li><li>'Tiong Bahru Plaza, UC800_101001_Chiller_1, Evaporator Saturated Refrigerant Temperature - Circuit 1 (Units: °C)'</li></ul> |
99
+ | 25 | <ul><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Header CHWS Temp'</li><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Header CHWS Temperature'</li><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Header CHWS Temperature'</li></ul> |
100
+ | 39 | <ul><li>' Chiller SC:Header Differential Pressure'</li></ul> |
101
+ | 23 | <ul><li>'Tiong Bahru Plaza, DDC-L20, PAHU TR-1 TEMPERATURE (Units: °C)'</li></ul> |
102
+ | 38 | <ul><li>'Wet Bulb Temperature'</li></ul> |
103
+ | 32 | <ul><li>'Tiong Bahru Plaza, UC800_3, Operating Mode'</li><li>'Tiong Bahru Plaza, UC800_101001_Chiller_1, Operating Mode'</li><li>'Tiong Bahru Plaza, UC800_102002_Chiller_2, Operating Mode'</li></ul> |
104
+ | 29 | <ul><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Head CWS Temp'</li><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Header CWS Temp'</li><li>'Tiong Bahru Plaza, SC-10, Chiller SC, Header CWS Temperature'</li></ul> |
105
+ | 22 | <ul><li>'Tiong Bahru Plaza, DDC B1-3, Pau-B1-02-DP Sensor'</li></ul> |
106
+ | 40 | <ul><li>'Tiong Bahru Plaza, UC800_102005, Cond Entering Water Temp (Units: °C)'</li><li>'Tiong Bahru Plaza, UC800_102004, Cond Leaving Water Temp (Units: °C)'</li><li>'Tiong Bahru Plaza, UC800_102004, Cond Leaving Water Temp (Units: °C)'</li></ul> |
107
+
108
+ ## Evaluation
109
+
110
+ ### Metrics
111
+ | Label | Accuracy |
112
+ |:--------|:---------|
113
+ | **all** | 0.8020 |
114
+
115
+ ## Uses
116
+
117
+ ### Direct Use for Inference
118
+
119
+ First install the SetFit library:
120
+
121
+ ```bash
122
+ pip install setfit
123
+ ```
124
+
125
+ Then you can load this model and run inference.
126
+
127
+ ```python
128
+ from setfit import SetFitModel
129
+
130
+ # Download from the 🤗 Hub
131
+ model = SetFitModel.from_pretrained("Varun1010/all-MiniLM-L6-v2-polaris-new-distilled")
132
+ # Run inference
133
+ preds = model("Tiong Bahru Plaza, DDC-L20, AHU 20-1 VSD CONTROL")
134
+ ```
135
+
136
+ <!--
137
+ ### Downstream Use
138
+
139
+ *List how someone could finetune this model on their own dataset.*
140
+ -->
141
+
142
+ <!--
143
+ ### Out-of-Scope Use
144
+
145
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
146
+ -->
147
+
148
+ <!--
149
+ ## Bias, Risks and Limitations
150
+
151
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
152
+ -->
153
+
154
+ <!--
155
+ ### Recommendations
156
+
157
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
158
+ -->
159
+
160
+ ## Training Details
161
+
162
+ ### Training Set Metrics
163
+ | Training set | Min | Median | Max |
164
+ |:-------------|:----|:-------|:----|
165
+ | Word count | 6 | 8.8589 | 14 |
166
+
167
+ | Label | Training Sample Count |
168
+ |:------|:----------------------|
169
+ | 0 | 10 |
170
+ | 1 | 10 |
171
+ | 2 | 10 |
172
+ | 3 | 10 |
173
+ | 4 | 10 |
174
+ | 5 | 10 |
175
+ | 6 | 10 |
176
+ | 7 | 10 |
177
+ | 8 | 10 |
178
+ | 9 | 10 |
179
+ | 10 | 10 |
180
+ | 11 | 10 |
181
+ | 12 | 10 |
182
+ | 13 | 10 |
183
+ | 14 | 10 |
184
+ | 15 | 10 |
185
+ | 16 | 10 |
186
+ | 17 | 10 |
187
+ | 18 | 3 |
188
+ | 19 | 3 |
189
+ | 20 | 10 |
190
+ | 21 | 10 |
191
+ | 22 | 1 |
192
+ | 23 | 1 |
193
+ | 24 | 10 |
194
+ | 25 | 4 |
195
+ | 26 | 10 |
196
+ | 27 | 8 |
197
+ | 28 | 4 |
198
+ | 29 | 3 |
199
+ | 30 | 3 |
200
+ | 31 | 4 |
201
+ | 32 | 4 |
202
+ | 33 | 6 |
203
+ | 34 | 6 |
204
+ | 35 | 5 |
205
+ | 36 | 3 |
206
+ | 37 | 3 |
207
+ | 38 | 1 |
208
+ | 39 | 1 |
209
+ | 40 | 3 |
210
+ | 41 | 10 |
211
+
212
+ ### Training Hyperparameters
213
+ - batch_size: (16, 16)
214
+ - num_epochs: (1, 16)
215
+ - max_steps: 500
216
+ - sampling_strategy: oversampling
217
+ - body_learning_rate: (2e-05, 1e-05)
218
+ - head_learning_rate: 0.01
219
+ - loss: CosineSimilarityLoss
220
+ - distance_metric: cosine_distance
221
+ - margin: 0.25
222
+ - end_to_end: False
223
+ - use_amp: False
224
+ - warmup_proportion: 0.1
225
+ - seed: 42
226
+ - eval_max_steps: -1
227
+ - load_best_model_at_end: False
228
+
229
+ ### Training Results
230
+ | Epoch | Step | Training Loss | Validation Loss |
231
+ |:------:|:----:|:-------------:|:---------------:|
232
+ | 0.0008 | 1 | 0.1765 | - |
233
+ | 0.0376 | 50 | 0.1212 | - |
234
+ | 0.0752 | 100 | 0.0674 | - |
235
+ | 0.1129 | 150 | 0.0589 | - |
236
+ | 0.1505 | 200 | 0.039 | - |
237
+ | 0.1881 | 250 | 0.0326 | - |
238
+ | 0.2257 | 300 | 0.0365 | - |
239
+ | 0.2634 | 350 | 0.0192 | - |
240
+ | 0.3010 | 400 | 0.0254 | - |
241
+ | 0.3386 | 450 | 0.0166 | - |
242
+ | 0.3762 | 500 | 0.0139 | - |
243
+ | 0.4138 | 550 | 0.0161 | - |
244
+ | 0.4515 | 600 | 0.0116 | - |
245
+ | 0.4891 | 650 | 0.0179 | - |
246
+ | 0.5267 | 700 | 0.0184 | - |
247
+ | 0.5643 | 750 | 0.0141 | - |
248
+ | 0.6020 | 800 | 0.0159 | - |
249
+ | 0.6396 | 850 | 0.0253 | - |
250
+ | 0.6772 | 900 | 0.0064 | - |
251
+ | 0.7148 | 950 | 0.0173 | - |
252
+ | 0.7524 | 1000 | 0.0172 | - |
253
+ | 0.7901 | 1050 | 0.0108 | - |
254
+ | 0.8277 | 1100 | 0.0055 | - |
255
+ | 0.8653 | 1150 | 0.0211 | - |
256
+ | 0.9029 | 1200 | 0.0053 | - |
257
+ | 0.9406 | 1250 | 0.0175 | - |
258
+ | 0.9782 | 1300 | 0.0112 | - |
259
+ | 1.0158 | 1350 | 0.005 | - |
260
+ | 1.0534 | 1400 | 0.0046 | - |
261
+ | 1.0910 | 1450 | 0.0072 | - |
262
+ | 1.1287 | 1500 | 0.0144 | - |
263
+ | 1.1663 | 1550 | 0.0284 | - |
264
+ | 1.2039 | 1600 | 0.0039 | - |
265
+ | 1.2415 | 1650 | 0.0157 | - |
266
+ | 1.2792 | 1700 | 0.014 | - |
267
+ | 1.3168 | 1750 | 0.0082 | - |
268
+ | 1.3544 | 1800 | 0.0029 | - |
269
+ | 1.3920 | 1850 | 0.0099 | - |
270
+ | 1.4296 | 1900 | 0.0037 | - |
271
+ | 1.4673 | 1950 | 0.0097 | - |
272
+ | 1.5049 | 2000 | 0.0064 | - |
273
+ | 1.5425 | 2050 | 0.0037 | - |
274
+ | 1.5801 | 2100 | 0.0042 | - |
275
+ | 1.6178 | 2150 | 0.0167 | - |
276
+ | 1.6554 | 2200 | 0.0062 | - |
277
+ | 1.6930 | 2250 | 0.0057 | - |
278
+ | 1.7306 | 2300 | 0.0072 | - |
279
+ | 1.7682 | 2350 | 0.017 | - |
280
+ | 1.8059 | 2400 | 0.0175 | - |
281
+ | 1.8435 | 2450 | 0.0067 | - |
282
+ | 1.8811 | 2500 | 0.0162 | - |
283
+ | 1.9187 | 2550 | 0.0058 | - |
284
+ | 1.9564 | 2600 | 0.0019 | - |
285
+ | 1.9940 | 2650 | 0.0171 | - |
286
+ | 2.0316 | 2700 | 0.0072 | - |
287
+ | 2.0692 | 2750 | 0.0034 | - |
288
+ | 2.1068 | 2800 | 0.0032 | - |
289
+ | 2.1445 | 2850 | 0.0054 | - |
290
+ | 2.1821 | 2900 | 0.0025 | - |
291
+ | 2.2197 | 2950 | 0.0047 | - |
292
+ | 2.2573 | 3000 | 0.0026 | - |
293
+ | 2.2950 | 3050 | 0.002 | - |
294
+ | 2.3326 | 3100 | 0.0043 | - |
295
+ | 2.3702 | 3150 | 0.0022 | - |
296
+ | 2.4078 | 3200 | 0.0036 | - |
297
+ | 2.4454 | 3250 | 0.0023 | - |
298
+ | 2.4831 | 3300 | 0.0018 | - |
299
+ | 2.5207 | 3350 | 0.0021 | - |
300
+ | 2.5583 | 3400 | 0.0026 | - |
301
+ | 2.5959 | 3450 | 0.003 | - |
302
+ | 2.6336 | 3500 | 0.0028 | - |
303
+ | 2.6712 | 3550 | 0.0025 | - |
304
+ | 2.7088 | 3600 | 0.0026 | - |
305
+ | 2.7464 | 3650 | 0.0018 | - |
306
+ | 2.7840 | 3700 | 0.0021 | - |
307
+ | 2.8217 | 3750 | 0.0107 | - |
308
+ | 2.8593 | 3800 | 0.0024 | - |
309
+ | 2.8969 | 3850 | 0.0022 | - |
310
+ | 2.9345 | 3900 | 0.0027 | - |
311
+ | 2.9722 | 3950 | 0.0023 | - |
312
+ | 3.0098 | 4000 | 0.0015 | - |
313
+ | 3.0474 | 4050 | 0.0035 | - |
314
+ | 3.0850 | 4100 | 0.0013 | - |
315
+ | 3.1226 | 4150 | 0.0014 | - |
316
+ | 3.1603 | 4200 | 0.0013 | - |
317
+ | 3.1979 | 4250 | 0.0015 | - |
318
+ | 3.2355 | 4300 | 0.0014 | - |
319
+ | 3.2731 | 4350 | 0.0022 | - |
320
+ | 3.3108 | 4400 | 0.0012 | - |
321
+ | 3.3484 | 4450 | 0.0018 | - |
322
+ | 3.3860 | 4500 | 0.0027 | - |
323
+ | 3.4236 | 4550 | 0.0014 | - |
324
+ | 3.4612 | 4600 | 0.001 | - |
325
+ | 3.4989 | 4650 | 0.0013 | - |
326
+ | 3.5365 | 4700 | 0.0013 | - |
327
+ | 3.5741 | 4750 | 0.0014 | - |
328
+ | 3.6117 | 4800 | 0.001 | - |
329
+ | 3.6494 | 4850 | 0.0012 | - |
330
+ | 3.6870 | 4900 | 0.0053 | - |
331
+ | 3.7246 | 4950 | 0.0025 | - |
332
+ | 3.7622 | 5000 | 0.0011 | - |
333
+ | 3.7998 | 5050 | 0.0013 | - |
334
+ | 3.8375 | 5100 | 0.0019 | - |
335
+ | 3.8751 | 5150 | 0.0012 | - |
336
+ | 3.9127 | 5200 | 0.0011 | - |
337
+ | 3.9503 | 5250 | 0.0013 | - |
338
+ | 3.9880 | 5300 | 0.0017 | - |
339
+ | 4.0256 | 5350 | 0.0013 | - |
340
+ | 4.0632 | 5400 | 0.0069 | - |
341
+ | 4.1008 | 5450 | 0.0009 | - |
342
+ | 4.1384 | 5500 | 0.0022 | - |
343
+ | 4.1761 | 5550 | 0.0013 | - |
344
+ | 4.2137 | 5600 | 0.0009 | - |
345
+ | 4.2513 | 5650 | 0.0011 | - |
346
+ | 4.2889 | 5700 | 0.0013 | - |
347
+ | 4.3266 | 5750 | 0.0014 | - |
348
+ | 4.3642 | 5800 | 0.0012 | - |
349
+ | 4.4018 | 5850 | 0.0014 | - |
350
+ | 4.4394 | 5900 | 0.0039 | - |
351
+ | 4.4771 | 5950 | 0.0011 | - |
352
+ | 4.5147 | 6000 | 0.0011 | - |
353
+ | 4.5523 | 6050 | 0.0012 | - |
354
+ | 4.5899 | 6100 | 0.0011 | - |
355
+ | 4.6275 | 6150 | 0.0024 | - |
356
+ | 4.6652 | 6200 | 0.0024 | - |
357
+ | 4.7028 | 6250 | 0.0039 | - |
358
+ | 4.7404 | 6300 | 0.0029 | - |
359
+ | 4.7780 | 6350 | 0.0015 | - |
360
+ | 4.8157 | 6400 | 0.0013 | - |
361
+ | 4.8533 | 6450 | 0.0007 | - |
362
+ | 4.8909 | 6500 | 0.0008 | - |
363
+ | 4.9285 | 6550 | 0.001 | - |
364
+ | 4.9661 | 6600 | 0.0012 | - |
365
+ | 0.0020 | 1 | 0.8538 | - |
366
+ | 0.0998 | 50 | 0.429 | - |
367
+ | 0.1996 | 100 | 0.0025 | - |
368
+ | 0.2994 | 150 | 0.0015 | - |
369
+ | 0.3992 | 200 | 0.0007 | - |
370
+ | 0.4990 | 250 | 0.0005 | - |
371
+ | 0.5988 | 300 | 0.0004 | - |
372
+ | 0.6986 | 350 | 0.0003 | - |
373
+ | 0.7984 | 400 | 0.0003 | - |
374
+ | 0.8982 | 450 | 0.0004 | - |
375
+ | 0.9980 | 500 | 0.0003 | - |
376
+
377
+ ### Framework Versions
378
+ - Python: 3.10.12
379
+ - SetFit: 1.0.3
380
+ - Sentence Transformers: 2.6.1
381
+ - Transformers: 4.38.2
382
+ - PyTorch: 2.2.1+cu121
383
+ - Datasets: 2.18.0
384
+ - Tokenizers: 0.15.2
385
+
386
+ ## Citation
387
+
388
+ ### BibTeX
389
+ ```bibtex
390
+ @article{https://doi.org/10.48550/arxiv.2209.11055,
391
+ doi = {10.48550/ARXIV.2209.11055},
392
+ url = {https://arxiv.org/abs/2209.11055},
393
+ author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
394
+ keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
395
+ title = {Efficient Few-Shot Learning Without Prompts},
396
+ publisher = {arXiv},
397
+ year = {2022},
398
+ copyright = {Creative Commons Attribution 4.0 International}
399
+ }
400
+ ```
401
+
402
+ <!--
403
+ ## Glossary
404
+
405
+ *Clearly define terms in order to be accessible across audiences.*
406
+ -->
407
+
408
+ <!--
409
+ ## Model Card Authors
410
+
411
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
412
+ -->
413
+
414
+ <!--
415
+ ## Model Card Contact
416
+
417
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
418
+ -->
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sentence-transformers/paraphrase-MiniLM-L3-v2",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 384,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 1536,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 3,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.38.2",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
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 +1,4 @@
 
 
 
 
 
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 sha256:6548eada8763047cb552fd86b99d225fec5bf3b95596101d5a27a8608bf1ca61
3
+ size 69565312
model_head.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3febdb9ec57873004b6df40be8d71902d42412d583e5cc59e71e4b0d5293377
3
+ size 112007
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": 128,
3
+ "do_lower_case": false
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "max_length": 128,
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "[PAD]",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "[SEP]",
57
+ "stride": 0,
58
+ "strip_accents": null,
59
+ "tokenize_chinese_chars": true,
60
+ "tokenizer_class": "BertTokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "[UNK]"
64
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff