Hugging Face's logo

gsjang
/
kepri-embedding

Feature Extraction
Transformers
PyTorch
roberta
text-embeddings-inference
Model card Files
xet
 Community
1
NTIS commited on
Commit
69863eb
·
verified ·
1 Parent(s): 198e4a6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -832
README.md CHANGED
@@ -1,832 +0,0 @@
1
- ---
2
- library_name: setfit
3
- metrics:
4
- - accuracy
5
- pipeline_tag: text-classification
6
- tags:
7
- - setfit
8
- - sentence-transformers
9
- - text-classification
10
- - generated_from_setfit_trainer
11
- widget:
12
- - text: 인공지능 챗봇 기술 향상에 대한 아이디어가 있는데, 관련된 역시 자세하 정보가 담긴 논문이나 보고서를 찾아줄래요?
13
- - text: 연구 자료의 서론 부분을 한 줄로 요약해 줄 수 있나요?
14
- - text: 우리 회사의 HR 정책 개선 방안에 대한 과제를 진행 중이야. 같은 주제의 이전 과제와 어떤 부분에서 왜 중복되었는지 궁금해
15
- - text: 초전도체의 임계 온도에 관한 연구 자료를 모으고 있어요. 여기에 관련된 유사한 연구나 보고서를 추천받고 싶어요
16
- - text: 공장에서 발생하는 가스 누출 문제 해결을 위한 시스템을 개발하려고 하는데, 이와 같은 측면에서 진행된 기존 연구나 비슷한 프로젝트가
17
- 있는지 알려주세요
18
- inference: true
19
- model-index:
20
- - name: SetFit
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: 0.9891304347826086
32
- name: Accuracy
33
- ---
34
-
35
- # SetFit
36
-
37
- This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. 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:** [Unknown](https://huggingface.co/unknown) -->
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:** 5 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
- | 오탈자 탐지 | <ul><li>'건축 프로젝트 설명 문장에서 오타나 잘못된 맞춤법을 찾아줘.'</li><li>'경영 보고서 내용에 대한 오탈자를 검토하고 수정해 드릴 수 있을까요?'</li><li>'경쟁사 분석 항목 내 문장 구성의 오류를 지적해주겠습니까?'</li></ul> |
66
- | 요약 | <ul><li>'(특정 논문 제목)의 결론 및 향후 연구 방향에 대해 요점을 정리해 주세요.'</li><li>'(특정 특허번호)를 기반으로 한 발명의 전체적인 개념을 짧게 설명 부탁드립니다.'</li><li>'1장의 데이터 수집 기술에 대해 요약해주세요'</li></ul> |
67
- | 유사문서 | <ul><li>'5G 통신 모듈 최적화에 관련된 프로젝트를 하고 있는데, 비슷한 내용의 프로젝트나 논문이 있는지 연결해서 말해줄래?'</li><li>'AI 기반 헬스케어 솔루션 개발에 관한 문헌 조사를 하고 있습니다. 와 같은 주제를 다룬 문서를 찾아줄 수 있을까요?'</li><li>'AI 연산 속도를 최적화하기 위한 반도체 설계 방식을 연구하고 있어. 관련된 유사한 논문이나 보고서를 찾고 싶어'</li></ul> |
68
- | 중복성 검토 | <ul><li>'5G 통신망을 기반으로 스마트 시티 구축에 관한 연구를 시작했어. 이와 동일하거나 겹치는 연구 과제나 프로젝트가 있는지 알아봐주고, 이유도 명확하게 밝혀줘'</li><li>'건물의 내진 설계 강화 방안을 조사하고 있는데 이에 연관된 기존 프로젝트가 무엇이 있는지 그리고 왜 겹치는지 말해줄래?'</li><li>'고성능 메모리 소자의 내구성을 향상시키는 기술을 개발하고 있어. 이와 비슷한 과제가 이전에 있었는지, 그리고 어떻게 유사하거나 중복되는지 말해줘'</li></ul> |
69
- | 특화 지식정보 제공 | <ul><li>'3D 금속 배선 기술(HBM, TSV)의 도입으로 인한 전력 소비 감소 방안에는 어떤 것이 있는가요?'</li><li>'AI 워크로드를 처리하기 위한 반도체 아키텍처 설계에서는 어떤 전략들이 사용되나요?'</li><li>'LEED 인증의 기준과 획득 과정에 대해 알고 싶습니다.'</li></ul> |
70
-
71
- ## Evaluation
72
-
73
- ### Metrics
74
- | Label | Accuracy |
75
- |:--------|:---------|
76
- | **all** | 0.9891 |
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("NTIS/kepri-embedding")
95
- # Run inference
96
- preds = model("연구 자료의 서론 부분을 한 줄로 요약해 줄 수 있나요?")
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 | 6 | 12.4709 | 27 |
129
-
130
- | Label | Training Sample Count |
131
- |:-----------|:----------------------|
132
- | 요약 | 105 |
133
- | 중복성 검토 | 78 |
134
- | 특화 지식정보 제공 | 106 |
135
- | 유사문서 | 115 |
136
- | 오탈자 탐지 | 95 |
137
-
138
- ### Training Hyperparameters
139
- - batch_size: (64, 64)
140
- - num_epochs: (10, 10)
141
- - max_steps: -1
142
- - sampling_strategy: oversampling
143
- - body_learning_rate: (2e-05, 1e-05)
144
- - head_learning_rate: 0.01
145
- - loss: CosineSimilarityLoss
146
- - distance_metric: cosine_distance
147
- - margin: 0.25
148
- - end_to_end: False
149
- - use_amp: False
150
- - warmup_proportion: 0.1
151
- - seed: 42
152
- - eval_max_steps: -1
153
- - load_best_model_at_end: True
154
-
155
- ### Training Results
156
- | Epoch | Step | Training Loss | Validation Loss |
157
- |:-------:|:--------:|:-------------:|:---------------:|
158
- | 0.0003 | 1 | 0.2062 | - |
159
- | 0.0161 | 50 | 0.2314 | - |
160
- | 0.0322 | 100 | 0.2008 | - |
161
- | 0.0484 | 150 | 0.1395 | - |
162
- | 0.0645 | 200 | 0.11 | - |
163
- | 0.0806 | 250 | 0.0872 | - |
164
- | 0.0967 | 300 | 0.0462 | - |
165
- | 0.1129 | 350 | 0.0188 | - |
166
- | 0.1290 | 400 | 0.0201 | - |
167
- | 0.1451 | 450 | 0.025 | - |
168
- | 0.1612 | 500 | 0.004 | - |
169
- | 0.1774 | 550 | 0.002 | - |
170
- | 0.1935 | 600 | 0.0153 | - |
171
- | 0.2096 | 650 | 0.0011 | - |
172
- | 0.2257 | 700 | 0.0007 | - |
173
- | 0.2419 | 750 | 0.0006 | - |
174
- | 0.2580 | 800 | 0.0006 | - |
175
- | 0.2741 | 850 | 0.0005 | - |
176
- | 0.2902 | 900 | 0.0004 | - |
177
- | 0.3064 | 950 | 0.0005 | - |
178
- | 0.3225 | 1000 | 0.0002 | - |
179
- | 0.3386 | 1050 | 0.0002 | - |
180
- | 0.3547 | 1100 | 0.0003 | - |
181
- | 0.3708 | 1150 | 0.0002 | - |
182
- | 0.3870 | 1200 | 0.0002 | - |
183
- | 0.4031 | 1250 | 0.0002 | - |
184
- | 0.4192 | 1300 | 0.0001 | - |
185
- | 0.4353 | 1350 | 0.0002 | - |
186
- | 0.4515 | 1400 | 0.0001 | - |
187
- | 0.4676 | 1450 | 0.0001 | - |
188
- | 0.4837 | 1500 | 0.0001 | - |
189
- | 0.4998 | 1550 | 0.0001 | - |
190
- | 0.5160 | 1600 | 0.0001 | - |
191
- | 0.5321 | 1650 | 0.0001 | - |
192
- | 0.5482 | 1700 | 0.0001 | - |
193
- | 0.5643 | 1750 | 0.0001 | - |
194
- | 0.5805 | 1800 | 0.0001 | - |
195
- | 0.5966 | 1850 | 0.0001 | - |
196
- | 0.6127 | 1900 | 0.0001 | - |
197
- | 0.6288 | 1950 | 0.0001 | - |
198
- | 0.6450 | 2000 | 0.0001 | - |
199
- | 0.6611 | 2050 | 0.0001 | - |
200
- | 0.6772 | 2100 | 0.0001 | - |
201
- | 0.6933 | 2150 | 0.0001 | - |
202
- | 0.7094 | 2200 | 0.0001 | - |
203
- | 0.7256 | 2250 | 0.0001 | - |
204
- | 0.7417 | 2300 | 0.0001 | - |
205
- | 0.7578 | 2350 | 0.0001 | - |
206
- | 0.7739 | 2400 | 0.0001 | - |
207
- | 0.7901 | 2450 | 0.0001 | - |
208
- | 0.8062 | 2500 | 0.0001 | - |
209
- | 0.8223 | 2550 | 0.0001 | - |
210
- | 0.8384 | 2600 | 0.0 | - |
211
- | 0.8546 | 2650 | 0.0 | - |
212
- | 0.8707 | 2700 | 0.0 | - |
213
- | 0.8868 | 2750 | 0.0001 | - |
214
- | 0.9029 | 2800 | 0.0 | - |
215
- | 0.9191 | 2850 | 0.0001 | - |
216
- | 0.9352 | 2900 | 0.0 | - |
217
- | 0.9513 | 2950 | 0.0 | - |
218
- | 0.9674 | 3000 | 0.0 | - |
219
- | 0.9836 | 3050 | 0.0 | - |
220
- | 0.9997 | 3100 | 0.0 | - |
221
- | **1.0** | **3101** | **-** | **0.0247** |
222
- | 1.0158 | 3150 | 0.0 | - |
223
- | 1.0319 | 3200 | 0.0 | - |
224
- | 1.0480 | 3250 | 0.0 | - |
225
- | 1.0642 | 3300 | 0.0001 | - |
226
- | 1.0803 | 3350 | 0.0 | - |
227
- | 1.0964 | 3400 | 0.0 | - |
228
- | 1.1125 | 3450 | 0.0 | - |
229
- | 1.1287 | 3500 | 0.0 | - |
230
- | 1.1448 | 3550 | 0.0 | - |
231
- | 1.1609 | 3600 | 0.0 | - |
232
- | 1.1770 | 3650 | 0.0 | - |
233
- | 1.1932 | 3700 | 0.0 | - |
234
- | 1.2093 | 3750 | 0.0 | - |
235
- | 1.2254 | 3800 | 0.0 | - |
236
- | 1.2415 | 3850 | 0.0 | - |
237
- | 1.2577 | 3900 | 0.0 | - |
238
- | 1.2738 | 3950 | 0.0 | - |
239
- | 1.2899 | 4000 | 0.0 | - |
240
- | 1.3060 | 4050 | 0.0 | - |
241
- | 1.3222 | 4100 | 0.0 | - |
242
- | 1.3383 | 4150 | 0.0 | - |
243
- | 1.3544 | 4200 | 0.0 | - |
244
- | 1.3705 | 4250 | 0.0 | - |
245
- | 1.3866 | 4300 | 0.0 | - |
246
- | 1.4028 | 4350 | 0.0 | - |
247
- | 1.4189 | 4400 | 0.0 | - |
248
- | 1.4350 | 4450 | 0.0 | - |
249
- | 1.4511 | 4500 | 0.0 | - |
250
- | 1.4673 | 4550 | 0.0 | - |
251
- | 1.4834 | 4600 | 0.0 | - |
252
- | 1.4995 | 4650 | 0.0 | - |
253
- | 1.5156 | 4700 | 0.0 | - |
254
- | 1.5318 | 4750 | 0.0 | - |
255
- | 1.5479 | 4800 | 0.0 | - |
256
- | 1.5640 | 4850 | 0.0 | - |
257
- | 1.5801 | 4900 | 0.0 | - |
258
- | 1.5963 | 4950 | 0.0 | - |
259
- | 1.6124 | 5000 | 0.0 | - |
260
- | 1.6285 | 5050 | 0.0 | - |
261
- | 1.6446 | 5100 | 0.0 | - |
262
- | 1.6608 | 5150 | 0.0 | - |
263
- | 1.6769 | 5200 | 0.0 | - |
264
- | 1.6930 | 5250 | 0.0 | - |
265
- | 1.7091 | 5300 | 0.0 | - |
266
- | 1.7252 | 5350 | 0.0 | - |
267
- | 1.7414 | 5400 | 0.0 | - |
268
- | 1.7575 | 5450 | 0.0 | - |
269
- | 1.7736 | 5500 | 0.0 | - |
270
- | 1.7897 | 5550 | 0.0 | - |
271
- | 1.8059 | 5600 | 0.0 | - |
272
- | 1.8220 | 5650 | 0.0 | - |
273
- | 1.8381 | 5700 | 0.0 | - |
274
- | 1.8542 | 5750 | 0.0 | - |
275
- | 1.8704 | 5800 | 0.0 | - |
276
- | 1.8865 | 5850 | 0.0 | - |
277
- | 1.9026 | 5900 | 0.0 | - |
278
- | 1.9187 | 5950 | 0.0 | - |
279
- | 1.9349 | 6000 | 0.0 | - |
280
- | 1.9510 | 6050 | 0.0 | - |
281
- | 1.9671 | 6100 | 0.0 | - |
282
- | 1.9832 | 6150 | 0.0 | - |
283
- | 1.9994 | 6200 | 0.0 | - |
284
- | 2.0 | 6202 | - | 0.0262 |
285
- | 2.0155 | 6250 | 0.0 | - |
286
- | 2.0316 | 6300 | 0.0 | - |
287
- | 2.0477 | 6350 | 0.0 | - |
288
- | 2.0639 | 6400 | 0.0 | - |
289
- | 2.0800 | 6450 | 0.0 | - |
290
- | 2.0961 | 6500 | 0.0 | - |
291
- | 2.1122 | 6550 | 0.0 | - |
292
- | 2.1283 | 6600 | 0.0 | - |
293
- | 2.1445 | 6650 | 0.0 | - |
294
- | 2.1606 | 6700 | 0.0 | - |
295
- | 2.1767 | 6750 | 0.0 | - |
296
- | 2.1928 | 6800 | 0.0 | - |
297
- | 2.2090 | 6850 | 0.0 | - |
298
- | 2.2251 | 6900 | 0.0 | - |
299
- | 2.2412 | 6950 | 0.0 | - |
300
- | 2.2573 | 7000 | 0.0 | - |
301
- | 2.2735 | 7050 | 0.0 | - |
302
- | 2.2896 | 7100 | 0.0 | - |
303
- | 2.3057 | 7150 | 0.0 | - |
304
- | 2.3218 | 7200 | 0.0 | - |
305
- | 2.3380 | 7250 | 0.0 | - |
306
- | 2.3541 | 7300 | 0.0 | - |
307
- | 2.3702 | 7350 | 0.0 | - |
308
- | 2.3863 | 7400 | 0.0 | - |
309
- | 2.4025 | 7450 | 0.0 | - |
310
- | 2.4186 | 7500 | 0.0 | - |
311
- | 2.4347 | 7550 | 0.0 | - |
312
- | 2.4508 | 7600 | 0.0 | - |
313
- | 2.4669 | 7650 | 0.0 | - |
314
- | 2.4831 | 7700 | 0.0 | - |
315
- | 2.4992 | 7750 | 0.0 | - |
316
- | 2.5153 | 7800 | 0.0 | - |
317
- | 2.5314 | 7850 | 0.0 | - |
318
- | 2.5476 | 7900 | 0.0 | - |
319
- | 2.5637 | 7950 | 0.0 | - |
320
- | 2.5798 | 8000 | 0.0 | - |
321
- | 2.5959 | 8050 | 0.0 | - |
322
- | 2.6121 | 8100 | 0.0 | - |
323
- | 2.6282 | 8150 | 0.0 | - |
324
- | 2.6443 | 8200 | 0.0 | - |
325
- | 2.6604 | 8250 | 0.0 | - |
326
- | 2.6766 | 8300 | 0.0 | - |
327
- | 2.6927 | 8350 | 0.0 | - |
328
- | 2.7088 | 8400 | 0.0 | - |
329
- | 2.7249 | 8450 | 0.0 | - |
330
- | 2.7411 | 8500 | 0.0 | - |
331
- | 2.7572 | 8550 | 0.0 | - |
332
- | 2.7733 | 8600 | 0.0 | - |
333
- | 2.7894 | 8650 | 0.0 | - |
334
- | 2.8055 | 8700 | 0.0 | - |
335
- | 2.8217 | 8750 | 0.0 | - |
336
- | 2.8378 | 8800 | 0.0 | - |
337
- | 2.8539 | 8850 | 0.0 | - |
338
- | 2.8700 | 8900 | 0.0 | - |
339
- | 2.8862 | 8950 | 0.0 | - |
340
- | 2.9023 | 9000 | 0.0 | - |
341
- | 2.9184 | 9050 | 0.0 | - |
342
- | 2.9345 | 9100 | 0.0 | - |
343
- | 2.9507 | 9150 | 0.0 | - |
344
- | 2.9668 | 9200 | 0.0 | - |
345
- | 2.9829 | 9250 | 0.0 | - |
346
- | 2.9990 | 9300 | 0.0 | - |
347
- | 3.0 | 9303 | - | 0.025 |
348
- | 3.0152 | 9350 | 0.0 | - |
349
- | 3.0313 | 9400 | 0.0 | - |
350
- | 3.0474 | 9450 | 0.0 | - |
351
- | 3.0635 | 9500 | 0.0 | - |
352
- | 3.0797 | 9550 | 0.0 | - |
353
- | 3.0958 | 9600 | 0.0 | - |
354
- | 3.1119 | 9650 | 0.0 | - |
355
- | 3.1280 | 9700 | 0.0 | - |
356
- | 3.1441 | 9750 | 0.0 | - |
357
- | 3.1603 | 9800 | 0.0 | - |
358
- | 3.1764 | 9850 | 0.0 | - |
359
- | 3.1925 | 9900 | 0.0 | - |
360
- | 3.2086 | 9950 | 0.0 | - |
361
- | 3.2248 | 10000 | 0.0 | - |
362
- | 3.2409 | 10050 | 0.0 | - |
363
- | 3.2570 | 10100 | 0.0 | - |
364
- | 3.2731 | 10150 | 0.0 | - |
365
- | 3.2893 | 10200 | 0.0 | - |
366
- | 3.3054 | 10250 | 0.0 | - |
367
- | 3.3215 | 10300 | 0.0 | - |
368
- | 3.3376 | 10350 | 0.0 | - |
369
- | 3.3538 | 10400 | 0.0 | - |
370
- | 3.3699 | 10450 | 0.0 | - |
371
- | 3.3860 | 10500 | 0.0 | - |
372
- | 3.4021 | 10550 | 0.0 | - |
373
- | 3.4183 | 10600 | 0.0 | - |
374
- | 3.4344 | 10650 | 0.0 | - |
375
- | 3.4505 | 10700 | 0.0 | - |
376
- | 3.4666 | 10750 | 0.0083 | - |
377
- | 3.4827 | 10800 | 0.0019 | - |
378
- | 3.4989 | 10850 | 0.0001 | - |
379
- | 3.5150 | 10900 | 0.0 | - |
380
- | 3.5311 | 10950 | 0.001 | - |
381
- | 3.5472 | 11000 | 0.0 | - |
382
- | 3.5634 | 11050 | 0.0 | - |
383
- | 3.5795 | 11100 | 0.0 | - |
384
- | 3.5956 | 11150 | 0.0 | - |
385
- | 3.6117 | 11200 | 0.0 | - |
386
- | 3.6279 | 11250 | 0.0 | - |
387
- | 3.6440 | 11300 | 0.0 | - |
388
- | 3.6601 | 11350 | 0.0 | - |
389
- | 3.6762 | 11400 | 0.0 | - |
390
- | 3.6924 | 11450 | 0.0 | - |
391
- | 3.7085 | 11500 | 0.0 | - |
392
- | 3.7246 | 11550 | 0.0 | - |
393
- | 3.7407 | 11600 | 0.0 | - |
394
- | 3.7569 | 11650 | 0.0 | - |
395
- | 3.7730 | 11700 | 0.0 | - |
396
- | 3.7891 | 11750 | 0.0 | - |
397
- | 3.8052 | 11800 | 0.0 | - |
398
- | 3.8213 | 11850 | 0.0 | - |
399
- | 3.8375 | 11900 | 0.0 | - |
400
- | 3.8536 | 11950 | 0.0 | - |
401
- | 3.8697 | 12000 | 0.0 | - |
402
- | 3.8858 | 12050 | 0.0 | - |
403
- | 3.9020 | 12100 | 0.0 | - |
404
- | 3.9181 | 12150 | 0.0 | - |
405
- | 3.9342 | 12200 | 0.0 | - |
406
- | 3.9503 | 12250 | 0.0 | - |
407
- | 3.9665 | 12300 | 0.0 | - |
408
- | 3.9826 | 12350 | 0.0 | - |
409
- | 3.9987 | 12400 | 0.0 | - |
410
- | 4.0 | 12404 | - | 0.0253 |
411
- | 4.0148 | 12450 | 0.0 | - |
412
- | 4.0310 | 12500 | 0.0 | - |
413
- | 4.0471 | 12550 | 0.0 | - |
414
- | 4.0632 | 12600 | 0.0 | - |
415
- | 4.0793 | 12650 | 0.0 | - |
416
- | 4.0955 | 12700 | 0.0 | - |
417
- | 4.1116 | 12750 | 0.0 | - |
418
- | 4.1277 | 12800 | 0.0 | - |
419
- | 4.1438 | 12850 | 0.0 | - |
420
- | 4.1599 | 12900 | 0.0 | - |
421
- | 4.1761 | 12950 | 0.0 | - |
422
- | 4.1922 | 13000 | 0.0 | - |
423
- | 4.2083 | 13050 | 0.0 | - |
424
- | 4.2244 | 13100 | 0.0 | - |
425
- | 4.2406 | 13150 | 0.0 | - |
426
- | 4.2567 | 13200 | 0.0 | - |
427
- | 4.2728 | 13250 | 0.0 | - |
428
- | 4.2889 | 13300 | 0.0 | - |
429
- | 4.3051 | 13350 | 0.0 | - |
430
- | 4.3212 | 13400 | 0.0 | - |
431
- | 4.3373 | 13450 | 0.0 | - |
432
- | 4.3534 | 13500 | 0.0 | - |
433
- | 4.3696 | 13550 | 0.0 | - |
434
- | 4.3857 | 13600 | 0.0 | - |
435
- | 4.4018 | 13650 | 0.0 | - |
436
- | 4.4179 | 13700 | 0.0 | - |
437
- | 4.4341 | 13750 | 0.0 | - |
438
- | 4.4502 | 13800 | 0.0 | - |
439
- | 4.4663 | 13850 | 0.0 | - |
440
- | 4.4824 | 13900 | 0.0 | - |
441
- | 4.4985 | 13950 | 0.0 | - |
442
- | 4.5147 | 14000 | 0.0 | - |
443
- | 4.5308 | 14050 | 0.0 | - |
444
- | 4.5469 | 14100 | 0.0 | - |
445
- | 4.5630 | 14150 | 0.0 | - |
446
- | 4.5792 | 14200 | 0.0 | - |
447
- | 4.5953 | 14250 | 0.0 | - |
448
- | 4.6114 | 14300 | 0.0 | - |
449
- | 4.6275 | 14350 | 0.0 | - |
450
- | 4.6437 | 14400 | 0.0 | - |
451
- | 4.6598 | 14450 | 0.0 | - |
452
- | 4.6759 | 14500 | 0.0 | - |
453
- | 4.6920 | 14550 | 0.0 | - |
454
- | 4.7082 | 14600 | 0.0 | - |
455
- | 4.7243 | 14650 | 0.0 | - |
456
- | 4.7404 | 14700 | 0.0 | - |
457
- | 4.7565 | 14750 | 0.0 | - |
458
- | 4.7727 | 14800 | 0.0 | - |
459
- | 4.7888 | 14850 | 0.0 | - |
460
- | 4.8049 | 14900 | 0.0 | - |
461
- | 4.8210 | 14950 | 0.0 | - |
462
- | 4.8371 | 15000 | 0.0 | - |
463
- | 4.8533 | 15050 | 0.0 | - |
464
- | 4.8694 | 15100 | 0.0 | - |
465
- | 4.8855 | 15150 | 0.0 | - |
466
- | 4.9016 | 15200 | 0.0 | - |
467
- | 4.9178 | 15250 | 0.0 | - |
468
- | 4.9339 | 15300 | 0.0 | - |
469
- | 4.9500 | 15350 | 0.0 | - |
470
- | 4.9661 | 15400 | 0.0 | - |
471
- | 4.9823 | 15450 | 0.0 | - |
472
- | 4.9984 | 15500 | 0.0 | - |
473
- | 5.0 | 15505 | - | 0.0259 |
474
- | 5.0145 | 15550 | 0.0 | - |
475
- | 5.0306 | 15600 | 0.0 | - |
476
- | 5.0468 | 15650 | 0.0 | - |
477
- | 5.0629 | 15700 | 0.0 | - |
478
- | 5.0790 | 15750 | 0.0 | - |
479
- | 5.0951 | 15800 | 0.0 | - |
480
- | 5.1113 | 15850 | 0.0 | - |
481
- | 5.1274 | 15900 | 0.0 | - |
482
- | 5.1435 | 15950 | 0.0 | - |
483
- | 5.1596 | 16000 | 0.0 | - |
484
- | 5.1757 | 16050 | 0.0 | - |
485
- | 5.1919 | 16100 | 0.0 | - |
486
- | 5.2080 | 16150 | 0.0 | - |
487
- | 5.2241 | 16200 | 0.0 | - |
488
- | 5.2402 | 16250 | 0.0 | - |
489
- | 5.2564 | 16300 | 0.0 | - |
490
- | 5.2725 | 16350 | 0.0 | - |
491
- | 5.2886 | 16400 | 0.0 | - |
492
- | 5.3047 | 16450 | 0.0 | - |
493
- | 5.3209 | 16500 | 0.0 | - |
494
- | 5.3370 | 16550 | 0.0 | - |
495
- | 5.3531 | 16600 | 0.0 | - |
496
- | 5.3692 | 16650 | 0.0 | - |
497
- | 5.3854 | 16700 | 0.0 | - |
498
- | 5.4015 | 16750 | 0.0 | - |
499
- | 5.4176 | 16800 | 0.0 | - |
500
- | 5.4337 | 16850 | 0.0 | - |
501
- | 5.4499 | 16900 | 0.0 | - |
502
- | 5.4660 | 16950 | 0.0 | - |
503
- | 5.4821 | 17000 | 0.0 | - |
504
- | 5.4982 | 17050 | 0.0 | - |
505
- | 5.5144 | 17100 | 0.0 | - |
506
- | 5.5305 | 17150 | 0.0 | - |
507
- | 5.5466 | 17200 | 0.0 | - |
508
- | 5.5627 | 17250 | 0.0 | - |
509
- | 5.5788 | 17300 | 0.0 | - |
510
- | 5.5950 | 17350 | 0.0 | - |
511
- | 5.6111 | 17400 | 0.0 | - |
512
- | 5.6272 | 17450 | 0.0 | - |
513
- | 5.6433 | 17500 | 0.0 | - |
514
- | 5.6595 | 17550 | 0.0 | - |
515
- | 5.6756 | 17600 | 0.0 | - |
516
- | 5.6917 | 17650 | 0.0 | - |
517
- | 5.7078 | 17700 | 0.0 | - |
518
- | 5.7240 | 17750 | 0.0 | - |
519
- | 5.7401 | 17800 | 0.0 | - |
520
- | 5.7562 | 17850 | 0.0 | - |
521
- | 5.7723 | 17900 | 0.0 | - |
522
- | 5.7885 | 17950 | 0.0 | - |
523
- | 5.8046 | 18000 | 0.0 | - |
524
- | 5.8207 | 18050 | 0.0 | - |
525
- | 5.8368 | 18100 | 0.0 | - |
526
- | 5.8530 | 18150 | 0.0 | - |
527
- | 5.8691 | 18200 | 0.0 | - |
528
- | 5.8852 | 18250 | 0.0 | - |
529
- | 5.9013 | 18300 | 0.0 | - |
530
- | 5.9174 | 18350 | 0.0 | - |
531
- | 5.9336 | 18400 | 0.0 | - |
532
- | 5.9497 | 18450 | 0.0 | - |
533
- | 5.9658 | 18500 | 0.0 | - |
534
- | 5.9819 | 18550 | 0.0 | - |
535
- | 5.9981 | 18600 | 0.0 | - |
536
- | 6.0 | 18606 | - | 0.0255 |
537
- | 6.0142 | 18650 | 0.0 | - |
538
- | 6.0303 | 18700 | 0.0 | - |
539
- | 6.0464 | 18750 | 0.0 | - |
540
- | 6.0626 | 18800 | 0.0 | - |
541
- | 6.0787 | 18850 | 0.0 | - |
542
- | 6.0948 | 18900 | 0.0 | - |
543
- | 6.1109 | 18950 | 0.0 | - |
544
- | 6.1271 | 19000 | 0.0 | - |
545
- | 6.1432 | 19050 | 0.0 | - |
546
- | 6.1593 | 19100 | 0.0 | - |
547
- | 6.1754 | 19150 | 0.0 | - |
548
- | 6.1916 | 19200 | 0.0 | - |
549
- | 6.2077 | 19250 | 0.0 | - |
550
- | 6.2238 | 19300 | 0.0 | - |
551
- | 6.2399 | 19350 | 0.0 | - |
552
- | 6.2560 | 19400 | 0.0 | - |
553
- | 6.2722 | 19450 | 0.0 | - |
554
- | 6.2883 | 19500 | 0.0 | - |
555
- | 6.3044 | 19550 | 0.0 | - |
556
- | 6.3205 | 19600 | 0.0 | - |
557
- | 6.3367 | 19650 | 0.0 | - |
558
- | 6.3528 | 19700 | 0.0 | - |
559
- | 6.3689 | 19750 | 0.0 | - |
560
- | 6.3850 | 19800 | 0.0 | - |
561
- | 6.4012 | 19850 | 0.0 | - |
562
- | 6.4173 | 19900 | 0.0 | - |
563
- | 6.4334 | 19950 | 0.0 | - |
564
- | 6.4495 | 20000 | 0.0 | - |
565
- | 6.4657 | 20050 | 0.0 | - |
566
- | 6.4818 | 20100 | 0.0 | - |
567
- | 6.4979 | 20150 | 0.0 | - |
568
- | 6.5140 | 20200 | 0.0 | - |
569
- | 6.5302 | 20250 | 0.0 | - |
570
- | 6.5463 | 20300 | 0.0 | - |
571
- | 6.5624 | 20350 | 0.0 | - |
572
- | 6.5785 | 20400 | 0.0 | - |
573
- | 6.5946 | 20450 | 0.0 | - |
574
- | 6.6108 | 20500 | 0.0 | - |
575
- | 6.6269 | 20550 | 0.0 | - |
576
- | 6.6430 | 20600 | 0.0 | - |
577
- | 6.6591 | 20650 | 0.0 | - |
578
- | 6.6753 | 20700 | 0.0 | - |
579
- | 6.6914 | 20750 | 0.0 | - |
580
- | 6.7075 | 20800 | 0.0 | - |
581
- | 6.7236 | 20850 | 0.0 | - |
582
- | 6.7398 | 20900 | 0.0 | - |
583
- | 6.7559 | 20950 | 0.0 | - |
584
- | 6.7720 | 21000 | 0.0 | - |
585
- | 6.7881 | 21050 | 0.0 | - |
586
- | 6.8043 | 21100 | 0.0 | - |
587
- | 6.8204 | 21150 | 0.0 | - |
588
- | 6.8365 | 21200 | 0.0 | - |
589
- | 6.8526 | 21250 | 0.0 | - |
590
- | 6.8688 | 21300 | 0.0 | - |
591
- | 6.8849 | 21350 | 0.0 | - |
592
- | 6.9010 | 21400 | 0.0 | - |
593
- | 6.9171 | 21450 | 0.0 | - |
594
- | 6.9332 | 21500 | 0.0 | - |
595
- | 6.9494 | 21550 | 0.0 | - |
596
- | 6.9655 | 21600 | 0.0 | - |
597
- | 6.9816 | 21650 | 0.0 | - |
598
- | 6.9977 | 21700 | 0.0 | - |
599
- | 7.0 | 21707 | - | 0.0264 |
600
- | 7.0139 | 21750 | 0.0 | - |
601
- | 7.0300 | 21800 | 0.0 | - |
602
- | 7.0461 | 21850 | 0.0 | - |
603
- | 7.0622 | 21900 | 0.0 | - |
604
- | 7.0784 | 21950 | 0.0 | - |
605
- | 7.0945 | 22000 | 0.0 | - |
606
- | 7.1106 | 22050 | 0.0 | - |
607
- | 7.1267 | 22100 | 0.0 | - |
608
- | 7.1429 | 22150 | 0.0 | - |
609
- | 7.1590 | 22200 | 0.0 | - |
610
- | 7.1751 | 22250 | 0.0 | - |
611
- | 7.1912 | 22300 | 0.0 | - |
612
- | 7.2074 | 22350 | 0.0 | - |
613
- | 7.2235 | 22400 | 0.0 | - |
614
- | 7.2396 | 22450 | 0.0 | - |
615
- | 7.2557 | 22500 | 0.0 | - |
616
- | 7.2718 | 22550 | 0.0 | - |
617
- | 7.2880 | 22600 | 0.0 | - |
618
- | 7.3041 | 22650 | 0.0 | - |
619
- | 7.3202 | 22700 | 0.0 | - |
620
- | 7.3363 | 22750 | 0.0 | - |
621
- | 7.3525 | 22800 | 0.0 | - |
622
- | 7.3686 | 22850 | 0.0 | - |
623
- | 7.3847 | 22900 | 0.0 | - |
624
- | 7.4008 | 22950 | 0.0 | - |
625
- | 7.4170 | 23000 | 0.0 | - |
626
- | 7.4331 | 23050 | 0.0 | - |
627
- | 7.4492 | 23100 | 0.0 | - |
628
- | 7.4653 | 23150 | 0.0 | - |
629
- | 7.4815 | 23200 | 0.0 | - |
630
- | 7.4976 | 23250 | 0.0 | - |
631
- | 7.5137 | 23300 | 0.0 | - |
632
- | 7.5298 | 23350 | 0.0 | - |
633
- | 7.5460 | 23400 | 0.0 | - |
634
- | 7.5621 | 23450 | 0.0 | - |
635
- | 7.5782 | 23500 | 0.0 | - |
636
- | 7.5943 | 23550 | 0.0 | - |
637
- | 7.6104 | 23600 | 0.0 | - |
638
- | 7.6266 | 23650 | 0.0 | - |
639
- | 7.6427 | 23700 | 0.0 | - |
640
- | 7.6588 | 23750 | 0.0 | - |
641
- | 7.6749 | 23800 | 0.0 | - |
642
- | 7.6911 | 23850 | 0.0 | - |
643
- | 7.7072 | 23900 | 0.0 | - |
644
- | 7.7233 | 23950 | 0.0 | - |
645
- | 7.7394 | 24000 | 0.0 | - |
646
- | 7.7556 | 24050 | 0.0 | - |
647
- | 7.7717 | 24100 | 0.0 | - |
648
- | 7.7878 | 24150 | 0.0 | - |
649
- | 7.8039 | 24200 | 0.0 | - |
650
- | 7.8201 | 24250 | 0.0 | - |
651
- | 7.8362 | 24300 | 0.0 | - |
652
- | 7.8523 | 24350 | 0.0 | - |
653
- | 7.8684 | 24400 | 0.0 | - |
654
- | 7.8846 | 24450 | 0.0 | - |
655
- | 7.9007 | 24500 | 0.0 | - |
656
- | 7.9168 | 24550 | 0.0 | - |
657
- | 7.9329 | 24600 | 0.0 | - |
658
- | 7.9490 | 24650 | 0.0 | - |
659
- | 7.9652 | 24700 | 0.0 | - |
660
- | 7.9813 | 24750 | 0.0 | - |
661
- | 7.9974 | 24800 | 0.0 | - |
662
- | 8.0 | 24808 | - | 0.0252 |
663
- | 8.0135 | 24850 | 0.0 | - |
664
- | 8.0297 | 24900 | 0.0 | - |
665
- | 8.0458 | 24950 | 0.0 | - |
666
- | 8.0619 | 25000 | 0.0 | - |
667
- | 8.0780 | 25050 | 0.0 | - |
668
- | 8.0942 | 25100 | 0.0 | - |
669
- | 8.1103 | 25150 | 0.0 | - |
670
- | 8.1264 | 25200 | 0.0 | - |
671
- | 8.1425 | 25250 | 0.0 | - |
672
- | 8.1587 | 25300 | 0.0 | - |
673
- | 8.1748 | 25350 | 0.0 | - |
674
- | 8.1909 | 25400 | 0.0 | - |
675
- | 8.2070 | 25450 | 0.0 | - |
676
- | 8.2232 | 25500 | 0.0 | - |
677
- | 8.2393 | 25550 | 0.0 | - |
678
- | 8.2554 | 25600 | 0.0 | - |
679
- | 8.2715 | 25650 | 0.0 | - |
680
- | 8.2876 | 25700 | 0.0 | - |
681
- | 8.3038 | 25750 | 0.0 | - |
682
- | 8.3199 | 25800 | 0.0 | - |
683
- | 8.3360 | 25850 | 0.0 | - |
684
- | 8.3521 | 25900 | 0.0 | - |
685
- | 8.3683 | 25950 | 0.0 | - |
686
- | 8.3844 | 26000 | 0.0 | - |
687
- | 8.4005 | 26050 | 0.0 | - |
688
- | 8.4166 | 26100 | 0.0 | - |
689
- | 8.4328 | 26150 | 0.0 | - |
690
- | 8.4489 | 26200 | 0.0 | - |
691
- | 8.4650 | 26250 | 0.0 | - |
692
- | 8.4811 | 26300 | 0.0 | - |
693
- | 8.4973 | 26350 | 0.0 | - |
694
- | 8.5134 | 26400 | 0.0 | - |
695
- | 8.5295 | 26450 | 0.0 | - |
696
- | 8.5456 | 26500 | 0.0 | - |
697
- | 8.5618 | 26550 | 0.0 | - |
698
- | 8.5779 | 26600 | 0.0 | - |
699
- | 8.5940 | 26650 | 0.0 | - |
700
- | 8.6101 | 26700 | 0.0 | - |
701
- | 8.6262 | 26750 | 0.0 | - |
702
- | 8.6424 | 26800 | 0.0 | - |
703
- | 8.6585 | 26850 | 0.0 | - |
704
- | 8.6746 | 26900 | 0.0 | - |
705
- | 8.6907 | 26950 | 0.0 | - |
706
- | 8.7069 | 27000 | 0.0 | - |
707
- | 8.7230 | 27050 | 0.0 | - |
708
- | 8.7391 | 27100 | 0.0 | - |
709
- | 8.7552 | 27150 | 0.0 | - |
710
- | 8.7714 | 27200 | 0.0 | - |
711
- | 8.7875 | 27250 | 0.0 | - |
712
- | 8.8036 | 27300 | 0.0 | - |
713
- | 8.8197 | 27350 | 0.0 | - |
714
- | 8.8359 | 27400 | 0.0 | - |
715
- | 8.8520 | 27450 | 0.0 | - |
716
- | 8.8681 | 27500 | 0.0 | - |
717
- | 8.8842 | 27550 | 0.0 | - |
718
- | 8.9004 | 27600 | 0.0 | - |
719
- | 8.9165 | 27650 | 0.0 | - |
720
- | 8.9326 | 27700 | 0.0 | - |
721
- | 8.9487 | 27750 | 0.0 | - |
722
- | 8.9649 | 27800 | 0.0 | - |
723
- | 8.9810 | 27850 | 0.0 | - |
724
- | 8.9971 | 27900 | 0.0 | - |
725
- | 9.0 | 27909 | - | 0.0255 |
726
- | 9.0132 | 27950 | 0.0 | - |
727
- | 9.0293 | 28000 | 0.0 | - |
728
- | 9.0455 | 28050 | 0.0 | - |
729
- | 9.0616 | 28100 | 0.0 | - |
730
- | 9.0777 | 28150 | 0.0 | - |
731
- | 9.0938 | 28200 | 0.0 | - |
732
- | 9.1100 | 28250 | 0.0 | - |
733
- | 9.1261 | 28300 | 0.0 | - |
734
- | 9.1422 | 28350 | 0.0 | - |
735
- | 9.1583 | 28400 | 0.0 | - |
736
- | 9.1745 | 28450 | 0.0 | - |
737
- | 9.1906 | 28500 | 0.0 | - |
738
- | 9.2067 | 28550 | 0.0 | - |
739
- | 9.2228 | 28600 | 0.0 | - |
740
- | 9.2390 | 28650 | 0.0 | - |
741
- | 9.2551 | 28700 | 0.0 | - |
742
- | 9.2712 | 28750 | 0.0 | - |
743
- | 9.2873 | 28800 | 0.0 | - |
744
- | 9.3035 | 28850 | 0.0 | - |
745
- | 9.3196 | 28900 | 0.0 | - |
746
- | 9.3357 | 28950 | 0.0 | - |
747
- | 9.3518 | 29000 | 0.0 | - |
748
- | 9.3679 | 29050 | 0.0 | - |
749
- | 9.3841 | 29100 | 0.0 | - |
750
- | 9.4002 | 29150 | 0.0 | - |
751
- | 9.4163 | 29200 | 0.0 | - |
752
- | 9.4324 | 29250 | 0.0 | - |
753
- | 9.4486 | 29300 | 0.0 | - |
754
- | 9.4647 | 29350 | 0.0 | - |
755
- | 9.4808 | 29400 | 0.0 | - |
756
- | 9.4969 | 29450 | 0.0 | - |
757
- | 9.5131 | 29500 | 0.0 | - |
758
- | 9.5292 | 29550 | 0.0 | - |
759
- | 9.5453 | 29600 | 0.0 | - |
760
- | 9.5614 | 29650 | 0.0 | - |
761
- | 9.5776 | 29700 | 0.0 | - |
762
- | 9.5937 | 29750 | 0.0 | - |
763
- | 9.6098 | 29800 | 0.0 | - |
764
- | 9.6259 | 29850 | 0.0 | - |
765
- | 9.6421 | 29900 | 0.0 | - |
766
- | 9.6582 | 29950 | 0.0 | - |
767
- | 9.6743 | 30000 | 0.0 | - |
768
- | 9.6904 | 30050 | 0.0 | - |
769
- | 9.7065 | 30100 | 0.0 | - |
770
- | 9.7227 | 30150 | 0.0 | - |
771
- | 9.7388 | 30200 | 0.0 | - |
772
- | 9.7549 | 30250 | 0.0 | - |
773
- | 9.7710 | 30300 | 0.0 | - |
774
- | 9.7872 | 30350 | 0.0 | - |
775
- | 9.8033 | 30400 | 0.0 | - |
776
- | 9.8194 | 30450 | 0.0 | - |
777
- | 9.8355 | 30500 | 0.0 | - |
778
- | 9.8517 | 30550 | 0.0 | - |
779
- | 9.8678 | 30600 | 0.0 | - |
780
- | 9.8839 | 30650 | 0.0 | - |
781
- | 9.9000 | 30700 | 0.0 | - |
782
- | 9.9162 | 30750 | 0.0 | - |
783
- | 9.9323 | 30800 | 0.0 | - |
784
- | 9.9484 | 30850 | 0.0 | - |
785
- | 9.9645 | 30900 | 0.0 | - |
786
- | 9.9807 | 30950 | 0.0 | - |
787
- | 9.9968 | 31000 | 0.0 | - |
788
- | 10.0 | 31010 | - | 0.0264 |
789
-
790
- * The bold row denotes the saved checkpoint.
791
- ### Framework Versions
792
- - Python: 3.9.18
793
- - SetFit: 1.0.3
794
- - Sentence Transformers: 2.2.1
795
- - Transformers: 4.32.1
796
- - PyTorch: 1.10.0
797
- - Datasets: 2.20.0
798
- - Tokenizers: 0.13.3
799
-
800
- ## Citation
801
-
802
- ### BibTeX
803
- ```bibtex
804
- @article{https://doi.org/10.48550/arxiv.2209.11055,
805
- doi = {10.48550/ARXIV.2209.11055},
806
- url = {https://arxiv.org/abs/2209.11055},
807
- author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
808
- keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
809
- title = {Efficient Few-Shot Learning Without Prompts},
810
- publisher = {arXiv},
811
- year = {2022},
812
- copyright = {Creative Commons Attribution 4.0 International}
813
- }
814
- ```
815
-
816
- <!--
817
- ## Glossary
818
-
819
- *Clearly define terms in order to be accessible across audiences.*
820
- -->
821
-
822
- <!--
823
- ## Model Card Authors
824
-
825
- *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
826
- -->
827
-
828
- <!--
829
- ## Model Card Contact
830
-
831
- *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
832
- -->