Hugging Face's logo

gsjang
/
sroberta-embedding

Text Classification
setfit
PyTorch
sentence-transformers
roberta
generated_from_setfit_trainer
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
Community
1
sroberta-embedding / README.md
NTIS
Add SetFit model
8c305f0 verified
preview code
|
raw
history blame contribute delete
49.3 kB
 ---
base_model: jhgan/ko-sroberta-multitask
library_name: setfit
metrics:
- accuracy
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: 제36조에 따른 수탁기관 정보 공시 방법은?
- text: 원장 인계 전 필요한 절차는?
- text: 미국에서 I140 허가 통지서 사본을 받으려면 어떻게 해야 하나요?
- text: 기술자문계획서 작성 시 연구일정과 기술보유자 선발 고려 이유는?
- text: 연구윤리활동비와 연구실안전관리비의 공통 경비 관리는?
inference: true
model-index:
- name: SetFit with jhgan/ko-sroberta-multitask
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: accuracy
value: 0.9951690821256038
name: Accuracy
---
# SetFit with jhgan/ko-sroberta-multitask
This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [jhgan/ko-sroberta-multitask](https://huggingface.co/jhgan/ko-sroberta-multitask) 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.
The model has been trained using an efficient few-shot learning technique that involves:
1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.
## Model Details
### Model Description
- **Model Type:** SetFit
- **Sentence Transformer body:** [jhgan/ko-sroberta-multitask](https://huggingface.co/jhgan/ko-sroberta-multitask)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **Maximum Sequence Length:** 128 tokens
- **Number of Classes:** 2 classes
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
### Model Labels
| Label | Examples |
|:--------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| rag | <ul><li>'QR코드 스캔 후 필요한 서류와 절차는?'</li><li>'연구용역사업의 원가계산서 관련, 일정 금액 이상 지출 승인은 누구에게 받나요?'</li><li>'계약부서 승인 없이 지급신청 시 주의할 점은?'</li></ul> |
| general | <ul><li>'아래 글의 요지 좀 설명해줘.\n \n 다른 문화권에서 온 여자와 데이트. 관계에 대해 좋은 점이 많이 있습니다. 공통된 직업적 관심사, 동일한 성욕, 그리고 서로를 존중한다는 점은 제게는 새로운 관계입니다(항상 남성에 대해 안 좋은 태도를 가진 여자들과만 사귀어 왔죠). 그녀는 저를 정말 사랑해요. \n \n 하지만 장기적인 생존 가능성에 대해 몇 가지 심각한 우려가 있습니다. 하나는 부모님에 관한 것입니다. 제 부모님은 우리가 사귀는 사이라는 사실을 알게 되자 "네가 미국에 머물 수 있는 티켓이라는 걸 기억하라"고 말씀하셨어요. 우리가 진짜 사귀는 사이라는 사실을 알게 된 부모님은 제가 얼마나 버는지 알고 싶어 하셨고(저는 대학원생입니다), 존경의 표시로 은퇴한 부모님을 부양하는 전통에 대해 제가 괜찮은지 확인하고 싶어 하셨습니다(부모님은 그런 도움이 필요 없을 만큼 잘 살고 계시지만요). 여자친구는 이에 대해 부모님의 의견에 동의하며 제가 괜찮지 않다면 돈을 더 벌어서 직접 해야 한다고 말했습니다. 또한 여자친구는 제가 이전에 결혼했고 지금은 이혼했다는 사실을 부모님이 \'절대 알 수 없다\'고 말합니다. \n \n 제가 극복하거나 간과할 수 있었던 다른 문제들도 있지만(한 가지 예로, 그녀는 사교적이지 않지만 저는 사교적입니다), 이러한 문제들이 결합되어 그녀와의 미래는 앞으로 많은 문제가 예고되어 있고 위험하다고 느낍니다. 이전 결혼 생활에서 저는 그런 징후를 무시하고 대가를 치렀고, 그 역사를 반복하고 싶지 않습니다. 동시에 저와 성적으로도 잘 어울리는 파트너가 있다는 것은 정말 좋은 일입니다. \n \n 다른 사람들은 이런 다문화적인 상황에서 어떤 경험을 했는지, 특히 장기적인 경험이 있다면 어떤지 궁금합니다.'</li><li>'너는 누구냐니까'</li><li>'문제와 몇 가지 답 옵션("A", "B", "C", "D"와 연관된)이 주어집니다. 상식적인 지식을 바탕으로 정답을 선택해야 합니다. 연상에 기반한 답은 피하고, 답안 세트는 연상을 넘어서는 상식을 파악하기 위해 의도적으로 선택된 것입니다. \'A\', \'B\', \'C\', \'D\', \'E\' 중 하나를 제외하고는 다른 문자를 생성하지 말고 각 문제에 대해 하나의 답만 작성하세요.\n\n폰이라는 이름은 매우 다재다능할 수 있지만, 모든 부품이 중요한 것은 무엇일까요?\n(A)체스 게임 (B)계획 (C)체스 세트 (D)체커 (E)노스 캐롤라이나'</li></ul> |
## Evaluation
### Metrics
| Label | Accuracy |
|:--------|:---------|
| **all** | 0.9952 |
## Uses
### Direct Use for Inference
First install the SetFit library:
```bash
pip install setfit
```
Then you can load this model and run inference.
```python
from setfit import SetFitModel
# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("NTIS/sroberta-embedding")
# Run inference
preds = model("원장 인계 전 필요한 절차는?")
```
<!--
### Downstream Use
*List how someone could finetune this model on their own dataset.*
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Set Metrics
| Training set | Min | Median | Max |
|:-------------|:----|:-------|:----|
| Word count | 2 | 24.824 | 722 |
| Label | Training Sample Count |
|:--------|:----------------------|
| rag | 553 |
| general | 447 |
### Training Hyperparameters
- batch_size: (64, 64)
- num_epochs: (4, 4)
- max_steps: -1
- sampling_strategy: oversampling
- body_learning_rate: (2e-05, 1e-05)
- head_learning_rate: 0.01
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: False
- use_amp: False
- warmup_proportion: 0.1
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: True
### Training Results
| Epoch | Step | Training Loss | Validation Loss |
|:-------:|:---------:|:-------------:|:---------------:|
| 0.0001 | 1 | 0.2655 | - |
| 0.0063 | 50 | 0.2091 | - |
| 0.0126 | 100 | 0.2327 | - |
| 0.0189 | 150 | 0.1578 | - |
| 0.0253 | 200 | 0.0836 | - |
| 0.0316 | 250 | 0.0274 | - |
| 0.0379 | 300 | 0.0068 | - |
| 0.0442 | 350 | 0.0032 | - |
| 0.0505 | 400 | 0.0013 | - |
| 0.0568 | 450 | 0.0012 | - |
| 0.0632 | 500 | 0.0009 | - |
| 0.0695 | 550 | 0.0006 | - |
| 0.0758 | 600 | 0.0004 | - |
| 0.0821 | 650 | 0.0004 | - |
| 0.0884 | 700 | 0.0003 | - |
| 0.0947 | 750 | 0.0003 | - |
| 0.1011 | 800 | 0.0003 | - |
| 0.1074 | 850 | 0.0002 | - |
| 0.1137 | 900 | 0.0002 | - |
| 0.1200 | 950 | 0.0002 | - |
| 0.1263 | 1000 | 0.0002 | - |
| 0.1326 | 1050 | 0.0001 | - |
| 0.1390 | 1100 | 0.0001 | - |
| 0.1453 | 1150 | 0.0001 | - |
| 0.1516 | 1200 | 0.0001 | - |
| 0.1579 | 1250 | 0.0001 | - |
| 0.1642 | 1300 | 0.0001 | - |
| 0.1705 | 1350 | 0.0001 | - |
| 0.1769 | 1400 | 0.0001 | - |
| 0.1832 | 1450 | 0.0001 | - |
| 0.1895 | 1500 | 0.0001 | - |
| 0.1958 | 1550 | 0.0001 | - |
| 0.2021 | 1600 | 0.0 | - |
| 0.2084 | 1650 | 0.0001 | - |
| 0.2148 | 1700 | 0.0001 | - |
| 0.2211 | 1750 | 0.0 | - |
| 0.2274 | 1800 | 0.0001 | - |
| 0.2337 | 1850 | 0.0 | - |
| 0.2400 | 1900 | 0.0 | - |
| 0.2463 | 1950 | 0.0 | - |
| 0.2527 | 2000 | 0.0 | - |
| 0.2590 | 2050 | 0.0 | - |
| 0.2653 | 2100 | 0.0 | - |
| 0.2716 | 2150 | 0.0 | - |
| 0.2779 | 2200 | 0.0 | - |
| 0.2842 | 2250 | 0.0 | - |
| 0.2906 | 2300 | 0.0 | - |
| 0.2969 | 2350 | 0.0 | - |
| 0.3032 | 2400 | 0.0 | - |
| 0.3095 | 2450 | 0.0 | - |
| 0.3158 | 2500 | 0.0 | - |
| 0.3221 | 2550 | 0.0 | - |
| 0.3284 | 2600 | 0.0 | - |
| 0.3348 | 2650 | 0.0 | - |
| 0.3411 | 2700 | 0.0 | - |
| 0.3474 | 2750 | 0.0 | - |
| 0.3537 | 2800 | 0.0 | - |
| 0.3600 | 2850 | 0.0 | - |
| 0.3663 | 2900 | 0.0 | - |
| 0.3727 | 2950 | 0.0 | - |
| 0.3790 | 3000 | 0.0 | - |
| 0.3853 | 3050 | 0.0 | - |
| 0.3916 | 3100 | 0.0 | - |
| 0.3979 | 3150 | 0.0 | - |
| 0.4042 | 3200 | 0.0 | - |
| 0.4106 | 3250 | 0.0 | - |
| 0.4169 | 3300 | 0.0 | - |
| 0.4232 | 3350 | 0.0 | - |
| 0.4295 | 3400 | 0.0 | - |
| 0.4358 | 3450 | 0.0 | - |
| 0.4421 | 3500 | 0.0 | - |
| 0.4485 | 3550 | 0.0 | - |
| 0.4548 | 3600 | 0.0 | - |
| 0.4611 | 3650 | 0.0 | - |
| 0.4674 | 3700 | 0.0 | - |
| 0.4737 | 3750 | 0.0 | - |
| 0.4800 | 3800 | 0.0 | - |
| 0.4864 | 3850 | 0.0 | - |
| 0.4927 | 3900 | 0.0 | - |
| 0.4990 | 3950 | 0.0 | - |
| 0.5053 | 4000 | 0.0 | - |
| 0.5116 | 4050 | 0.0 | - |
| 0.5179 | 4100 | 0.0 | - |
| 0.5243 | 4150 | 0.0 | - |
| 0.5306 | 4200 | 0.0 | - |
| 0.5369 | 4250 | 0.0 | - |
| 0.5432 | 4300 | 0.0 | - |
| 0.5495 | 4350 | 0.0004 | - |
| 0.5558 | 4400 | 0.0001 | - |
| 0.5622 | 4450 | 0.0 | - |
| 0.5685 | 4500 | 0.0096 | - |
| 0.5748 | 4550 | 0.0 | - |
| 0.5811 | 4600 | 0.0 | - |
| 0.5874 | 4650 | 0.0 | - |
| 0.5937 | 4700 | 0.0 | - |
| 0.6001 | 4750 | 0.0 | - |
| 0.6064 | 4800 | 0.0 | - |
| 0.6127 | 4850 | 0.0 | - |
| 0.6190 | 4900 | 0.0 | - |
| 0.6253 | 4950 | 0.0 | - |
| 0.6316 | 5000 | 0.0 | - |
| 0.6379 | 5050 | 0.0 | - |
| 0.6443 | 5100 | 0.0 | - |
| 0.6506 | 5150 | 0.0 | - |
| 0.6569 | 5200 | 0.0 | - |
| 0.6632 | 5250 | 0.0 | - |
| 0.6695 | 5300 | 0.0 | - |
| 0.6758 | 5350 | 0.0 | - |
| 0.6822 | 5400 | 0.0 | - |
| 0.6885 | 5450 | 0.0 | - |
| 0.6948 | 5500 | 0.0 | - |
| 0.7011 | 5550 | 0.0 | - |
| 0.7074 | 5600 | 0.0 | - |
| 0.7137 | 5650 | 0.0 | - |
| 0.7201 | 5700 | 0.0 | - |
| 0.7264 | 5750 | 0.0 | - |
| 0.7327 | 5800 | 0.0 | - |
| 0.7390 | 5850 | 0.0 | - |
| 0.7453 | 5900 | 0.0 | - |
| 0.7516 | 5950 | 0.0 | - |
| 0.7580 | 6000 | 0.0 | - |
| 0.7643 | 6050 | 0.0 | - |
| 0.7706 | 6100 | 0.0 | - |
| 0.7769 | 6150 | 0.0 | - |
| 0.7832 | 6200 | 0.0 | - |
| 0.7895 | 6250 | 0.0 | - |
| 0.7959 | 6300 | 0.0 | - |
| 0.8022 | 6350 | 0.0 | - |
| 0.8085 | 6400 | 0.0 | - |
| 0.8148 | 6450 | 0.0 | - |
| 0.8211 | 6500 | 0.0 | - |
| 0.8274 | 6550 | 0.0 | - |
| 0.8338 | 6600 | 0.0 | - |
| 0.8401 | 6650 | 0.0 | - |
| 0.8464 | 6700 | 0.0 | - |
| 0.8527 | 6750 | 0.0 | - |
| 0.8590 | 6800 | 0.0 | - |
| 0.8653 | 6850 | 0.0 | - |
| 0.8717 | 6900 | 0.0 | - |
| 0.8780 | 6950 | 0.0 | - |
| 0.8843 | 7000 | 0.0 | - |
| 0.8906 | 7050 | 0.0 | - |
| 0.8969 | 7100 | 0.0 | - |
| 0.9032 | 7150 | 0.0 | - |
| 0.9096 | 7200 | 0.0 | - |
| 0.9159 | 7250 | 0.0 | - |
| 0.9222 | 7300 | 0.0 | - |
| 0.9285 | 7350 | 0.0 | - |
| 0.9348 | 7400 | 0.0 | - |
| 0.9411 | 7450 | 0.0 | - |
| 0.9474 | 7500 | 0.0 | - |
| 0.9538 | 7550 | 0.0 | - |
| 0.9601 | 7600 | 0.0 | - |
| 0.9664 | 7650 | 0.0 | - |
| 0.9727 | 7700 | 0.0 | - |
| 0.9790 | 7750 | 0.0 | - |
| 0.9853 | 7800 | 0.0 | - |
| 0.9917 | 7850 | 0.0 | - |
| 0.9980 | 7900 | 0.0 | - |
| 1.0 | 7916 | - | 0.0096 |
| 1.0043 | 7950 | 0.0 | - |
| 1.0106 | 8000 | 0.0 | - |
| 1.0169 | 8050 | 0.0 | - |
| 1.0232 | 8100 | 0.0 | - |
| 1.0296 | 8150 | 0.0 | - |
| 1.0359 | 8200 | 0.0 | - |
| 1.0422 | 8250 | 0.0 | - |
| 1.0485 | 8300 | 0.0 | - |
| 1.0548 | 8350 | 0.0 | - |
| 1.0611 | 8400 | 0.0 | - |
| 1.0675 | 8450 | 0.0 | - |
| 1.0738 | 8500 | 0.0 | - |
| 1.0801 | 8550 | 0.0 | - |
| 1.0864 | 8600 | 0.0 | - |
| 1.0927 | 8650 | 0.0 | - |
| 1.0990 | 8700 | 0.0 | - |
| 1.1054 | 8750 | 0.0 | - |
| 1.1117 | 8800 | 0.0 | - |
| 1.1180 | 8850 | 0.0 | - |
| 1.1243 | 8900 | 0.0 | - |
| 1.1306 | 8950 | 0.0 | - |
| 1.1369 | 9000 | 0.0 | - |
| 1.1433 | 9050 | 0.0 | - |
| 1.1496 | 9100 | 0.0 | - |
| 1.1559 | 9150 | 0.0 | - |
| 1.1622 | 9200 | 0.0 | - |
| 1.1685 | 9250 | 0.0 | - |
| 1.1748 | 9300 | 0.0 | - |
| 1.1812 | 9350 | 0.0 | - |
| 1.1875 | 9400 | 0.0 | - |
| 1.1938 | 9450 | 0.0 | - |
| 1.2001 | 9500 | 0.0 | - |
| 1.2064 | 9550 | 0.0 | - |
| 1.2127 | 9600 | 0.0 | - |
| 1.2191 | 9650 | 0.0 | - |
| 1.2254 | 9700 | 0.0 | - |
| 1.2317 | 9750 | 0.0 | - |
| 1.2380 | 9800 | 0.0 | - |
| 1.2443 | 9850 | 0.0 | - |
| 1.2506 | 9900 | 0.0 | - |
| 1.2569 | 9950 | 0.0 | - |
| 1.2633 | 10000 | 0.0 | - |
| 1.2696 | 10050 | 0.0 | - |
| 1.2759 | 10100 | 0.0 | - |
| 1.2822 | 10150 | 0.0 | - |
| 1.2885 | 10200 | 0.0 | - |
| 1.2948 | 10250 | 0.0 | - |
| 1.3012 | 10300 | 0.0 | - |
| 1.3075 | 10350 | 0.0 | - |
| 1.3138 | 10400 | 0.0 | - |
| 1.3201 | 10450 | 0.0 | - |
| 1.3264 | 10500 | 0.0 | - |
| 1.3327 | 10550 | 0.0 | - |
| 1.3391 | 10600 | 0.0 | - |
| 1.3454 | 10650 | 0.0 | - |
| 1.3517 | 10700 | 0.0 | - |
| 1.3580 | 10750 | 0.0 | - |
| 1.3643 | 10800 | 0.0 | - |
| 1.3706 | 10850 | 0.0 | - |
| 1.3770 | 10900 | 0.0 | - |
| 1.3833 | 10950 | 0.0 | - |
| 1.3896 | 11000 | 0.0 | - |
| 1.3959 | 11050 | 0.0 | - |
| 1.4022 | 11100 | 0.0 | - |
| 1.4085 | 11150 | 0.0 | - |
| 1.4149 | 11200 | 0.0 | - |
| 1.4212 | 11250 | 0.0 | - |
| 1.4275 | 11300 | 0.0 | - |
| 1.4338 | 11350 | 0.0 | - |
| 1.4401 | 11400 | 0.0 | - |
| 1.4464 | 11450 | 0.0 | - |
| 1.4528 | 11500 | 0.0 | - |
| 1.4591 | 11550 | 0.0 | - |
| 1.4654 | 11600 | 0.0 | - |
| 1.4717 | 11650 | 0.0 | - |
| 1.4780 | 11700 | 0.0 | - |
| 1.4843 | 11750 | 0.0 | - |
| 1.4907 | 11800 | 0.0 | - |
| 1.4970 | 11850 | 0.0 | - |
| 1.5033 | 11900 | 0.0 | - |
| 1.5096 | 11950 | 0.0 | - |
| 1.5159 | 12000 | 0.0 | - |
| 1.5222 | 12050 | 0.0 | - |
| 1.5285 | 12100 | 0.0 | - |
| 1.5349 | 12150 | 0.0 | - |
| 1.5412 | 12200 | 0.0 | - |
| 1.5475 | 12250 | 0.0 | - |
| 1.5538 | 12300 | 0.0 | - |
| 1.5601 | 12350 | 0.0 | - |
| 1.5664 | 12400 | 0.0 | - |
| 1.5728 | 12450 | 0.0 | - |
| 1.5791 | 12500 | 0.0 | - |
| 1.5854 | 12550 | 0.0 | - |
| 1.5917 | 12600 | 0.0 | - |
| 1.5980 | 12650 | 0.0 | - |
| 1.6043 | 12700 | 0.0 | - |
| 1.6107 | 12750 | 0.0 | - |
| 1.6170 | 12800 | 0.0 | - |
| 1.6233 | 12850 | 0.0 | - |
| 1.6296 | 12900 | 0.0 | - |
| 1.6359 | 12950 | 0.0 | - |
| 1.6422 | 13000 | 0.0 | - |
| 1.6486 | 13050 | 0.0 | - |
| 1.6549 | 13100 | 0.0 | - |
| 1.6612 | 13150 | 0.0 | - |
| 1.6675 | 13200 | 0.0 | - |
| 1.6738 | 13250 | 0.0 | - |
| 1.6801 | 13300 | 0.0 | - |
| 1.6865 | 13350 | 0.0 | - |
| 1.6928 | 13400 | 0.0 | - |
| 1.6991 | 13450 | 0.0 | - |
| 1.7054 | 13500 | 0.0 | - |
| 1.7117 | 13550 | 0.0 | - |
| 1.7180 | 13600 | 0.0 | - |
| 1.7244 | 13650 | 0.0 | - |
| 1.7307 | 13700 | 0.0 | - |
| 1.7370 | 13750 | 0.0 | - |
| 1.7433 | 13800 | 0.0 | - |
| 1.7496 | 13850 | 0.0 | - |
| 1.7559 | 13900 | 0.0 | - |
| 1.7623 | 13950 | 0.0 | - |
| 1.7686 | 14000 | 0.0 | - |
| 1.7749 | 14050 | 0.0 | - |
| 1.7812 | 14100 | 0.0 | - |
| 1.7875 | 14150 | 0.0 | - |
| 1.7938 | 14200 | 0.0 | - |
| 1.8002 | 14250 | 0.0 | - |
| 1.8065 | 14300 | 0.0 | - |
| 1.8128 | 14350 | 0.0 | - |
| 1.8191 | 14400 | 0.0 | - |
| 1.8254 | 14450 | 0.0 | - |
| 1.8317 | 14500 | 0.0 | - |
| 1.8380 | 14550 | 0.0 | - |
| 1.8444 | 14600 | 0.0 | - |
| 1.8507 | 14650 | 0.0 | - |
| 1.8570 | 14700 | 0.0 | - |
| 1.8633 | 14750 | 0.0 | - |
| 1.8696 | 14800 | 0.0 | - |
| 1.8759 | 14850 | 0.0 | - |
| 1.8823 | 14900 | 0.0 | - |
| 1.8886 | 14950 | 0.0 | - |
| 1.8949 | 15000 | 0.0 | - |
| 1.9012 | 15050 | 0.0 | - |
| 1.9075 | 15100 | 0.0 | - |
| 1.9138 | 15150 | 0.0 | - |
| 1.9202 | 15200 | 0.0 | - |
| 1.9265 | 15250 | 0.0 | - |
| 1.9328 | 15300 | 0.0 | - |
| 1.9391 | 15350 | 0.0 | - |
| 1.9454 | 15400 | 0.0 | - |
| 1.9517 | 15450 | 0.0 | - |
| 1.9581 | 15500 | 0.0 | - |
| 1.9644 | 15550 | 0.0 | - |
| 1.9707 | 15600 | 0.0 | - |
| 1.9770 | 15650 | 0.0 | - |
| 1.9833 | 15700 | 0.0 | - |
| 1.9896 | 15750 | 0.0 | - |
| 1.9960 | 15800 | 0.0 | - |
| **2.0** | **15832** | **-** | **0.0096** |
| 2.0023 | 15850 | 0.0 | - |
| 2.0086 | 15900 | 0.0 | - |
| 2.0149 | 15950 | 0.0 | - |
| 2.0212 | 16000 | 0.0 | - |
| 2.0275 | 16050 | 0.0 | - |
| 2.0339 | 16100 | 0.0 | - |
| 2.0402 | 16150 | 0.0 | - |
| 2.0465 | 16200 | 0.0 | - |
| 2.0528 | 16250 | 0.0 | - |
| 2.0591 | 16300 | 0.0 | - |
| 2.0654 | 16350 | 0.0 | - |
| 2.0718 | 16400 | 0.0 | - |
| 2.0781 | 16450 | 0.0 | - |
| 2.0844 | 16500 | 0.0 | - |
| 2.0907 | 16550 | 0.0 | - |
| 2.0970 | 16600 | 0.0 | - |
| 2.1033 | 16650 | 0.0 | - |
| 2.1097 | 16700 | 0.0 | - |
| 2.1160 | 16750 | 0.0 | - |
| 2.1223 | 16800 | 0.0 | - |
| 2.1286 | 16850 | 0.0 | - |
| 2.1349 | 16900 | 0.0 | - |
| 2.1412 | 16950 | 0.0 | - |
| 2.1475 | 17000 | 0.0 | - |
| 2.1539 | 17050 | 0.0 | - |
| 2.1602 | 17100 | 0.0 | - |
| 2.1665 | 17150 | 0.0 | - |
| 2.1728 | 17200 | 0.0 | - |
| 2.1791 | 17250 | 0.0 | - |
| 2.1854 | 17300 | 0.0 | - |
| 2.1918 | 17350 | 0.0 | - |
| 2.1981 | 17400 | 0.0 | - |
| 2.2044 | 17450 | 0.0 | - |
| 2.2107 | 17500 | 0.0 | - |
| 2.2170 | 17550 | 0.0 | - |
| 2.2233 | 17600 | 0.0 | - |
| 2.2297 | 17650 | 0.0 | - |
| 2.2360 | 17700 | 0.0 | - |
| 2.2423 | 17750 | 0.0 | - |
| 2.2486 | 17800 | 0.0 | - |
| 2.2549 | 17850 | 0.0 | - |
| 2.2612 | 17900 | 0.0 | - |
| 2.2676 | 17950 | 0.0 | - |
| 2.2739 | 18000 | 0.0 | - |
| 2.2802 | 18050 | 0.0 | - |
| 2.2865 | 18100 | 0.0 | - |
| 2.2928 | 18150 | 0.0 | - |
| 2.2991 | 18200 | 0.0 | - |
| 2.3055 | 18250 | 0.0 | - |
| 2.3118 | 18300 | 0.0 | - |
| 2.3181 | 18350 | 0.0 | - |
| 2.3244 | 18400 | 0.0 | - |
| 2.3307 | 18450 | 0.0 | - |
| 2.3370 | 18500 | 0.0 | - |
| 2.3434 | 18550 | 0.0 | - |
| 2.3497 | 18600 | 0.0 | - |
| 2.3560 | 18650 | 0.0 | - |
| 2.3623 | 18700 | 0.0 | - |
| 2.3686 | 18750 | 0.0 | - |
| 2.3749 | 18800 | 0.0 | - |
| 2.3813 | 18850 | 0.0 | - |
| 2.3876 | 18900 | 0.0 | - |
| 2.3939 | 18950 | 0.0 | - |
| 2.4002 | 19000 | 0.0 | - |
| 2.4065 | 19050 | 0.0 | - |
| 2.4128 | 19100 | 0.0 | - |
| 2.4192 | 19150 | 0.0 | - |
| 2.4255 | 19200 | 0.0 | - |
| 2.4318 | 19250 | 0.0 | - |
| 2.4381 | 19300 | 0.0 | - |
| 2.4444 | 19350 | 0.0 | - |
| 2.4507 | 19400 | 0.0 | - |
| 2.4570 | 19450 | 0.0 | - |
| 2.4634 | 19500 | 0.0 | - |
| 2.4697 | 19550 | 0.0 | - |
| 2.4760 | 19600 | 0.0 | - |
| 2.4823 | 19650 | 0.0 | - |
| 2.4886 | 19700 | 0.0 | - |
| 2.4949 | 19750 | 0.0 | - |
| 2.5013 | 19800 | 0.0 | - |
| 2.5076 | 19850 | 0.0 | - |
| 2.5139 | 19900 | 0.0 | - |
| 2.5202 | 19950 | 0.0 | - |
| 2.5265 | 20000 | 0.0 | - |
| 2.5328 | 20050 | 0.0 | - |
| 2.5392 | 20100 | 0.0 | - |
| 2.5455 | 20150 | 0.0 | - |
| 2.5518 | 20200 | 0.0 | - |
| 2.5581 | 20250 | 0.0 | - |
| 2.5644 | 20300 | 0.0 | - |
| 2.5707 | 20350 | 0.0 | - |
| 2.5771 | 20400 | 0.0 | - |
| 2.5834 | 20450 | 0.0 | - |
| 2.5897 | 20500 | 0.0 | - |
| 2.5960 | 20550 | 0.0 | - |
| 2.6023 | 20600 | 0.0 | - |
| 2.6086 | 20650 | 0.0 | - |
| 2.6150 | 20700 | 0.0 | - |
| 2.6213 | 20750 | 0.0 | - |
| 2.6276 | 20800 | 0.0 | - |
| 2.6339 | 20850 | 0.0 | - |
| 2.6402 | 20900 | 0.0 | - |
| 2.6465 | 20950 | 0.0 | - |
| 2.6529 | 21000 | 0.0 | - |
| 2.6592 | 21050 | 0.0 | - |
| 2.6655 | 21100 | 0.0 | - |
| 2.6718 | 21150 | 0.0 | - |
| 2.6781 | 21200 | 0.0 | - |
| 2.6844 | 21250 | 0.0 | - |
| 2.6908 | 21300 | 0.0 | - |
| 2.6971 | 21350 | 0.0 | - |
| 2.7034 | 21400 | 0.0 | - |
| 2.7097 | 21450 | 0.0 | - |
| 2.7160 | 21500 | 0.0 | - |
| 2.7223 | 21550 | 0.0 | - |
| 2.7287 | 21600 | 0.0 | - |
| 2.7350 | 21650 | 0.0 | - |
| 2.7413 | 21700 | 0.0 | - |
| 2.7476 | 21750 | 0.0 | - |
| 2.7539 | 21800 | 0.0 | - |
| 2.7602 | 21850 | 0.0 | - |
| 2.7665 | 21900 | 0.0 | - |
| 2.7729 | 21950 | 0.0 | - |
| 2.7792 | 22000 | 0.0 | - |
| 2.7855 | 22050 | 0.0 | - |
| 2.7918 | 22100 | 0.0 | - |
| 2.7981 | 22150 | 0.0 | - |
| 2.8044 | 22200 | 0.0 | - |
| 2.8108 | 22250 | 0.0 | - |
| 2.8171 | 22300 | 0.0 | - |
| 2.8234 | 22350 | 0.0 | - |
| 2.8297 | 22400 | 0.0 | - |
| 2.8360 | 22450 | 0.0 | - |
| 2.8423 | 22500 | 0.0 | - |
| 2.8487 | 22550 | 0.0 | - |
| 2.8550 | 22600 | 0.0 | - |
| 2.8613 | 22650 | 0.0 | - |
| 2.8676 | 22700 | 0.0 | - |
| 2.8739 | 22750 | 0.0 | - |
| 2.8802 | 22800 | 0.0 | - |
| 2.8866 | 22850 | 0.0 | - |
| 2.8929 | 22900 | 0.0 | - |
| 2.8992 | 22950 | 0.0 | - |
| 2.9055 | 23000 | 0.0 | - |
| 2.9118 | 23050 | 0.0 | - |
| 2.9181 | 23100 | 0.0 | - |
| 2.9245 | 23150 | 0.0 | - |
| 2.9308 | 23200 | 0.0 | - |
| 2.9371 | 23250 | 0.0 | - |
| 2.9434 | 23300 | 0.0 | - |
| 2.9497 | 23350 | 0.0 | - |
| 2.9560 | 23400 | 0.0 | - |
| 2.9624 | 23450 | 0.0 | - |
| 2.9687 | 23500 | 0.0 | - |
| 2.9750 | 23550 | 0.0 | - |
| 2.9813 | 23600 | 0.0 | - |
| 2.9876 | 23650 | 0.0 | - |
| 2.9939 | 23700 | 0.0 | - |
| 3.0 | 23748 | - | 0.0128 |
| 3.0003 | 23750 | 0.0 | - |
| 3.0066 | 23800 | 0.0 | - |
| 3.0129 | 23850 | 0.0 | - |
| 3.0192 | 23900 | 0.0 | - |
| 3.0255 | 23950 | 0.0 | - |
| 3.0318 | 24000 | 0.0 | - |
| 3.0382 | 24050 | 0.0 | - |
| 3.0445 | 24100 | 0.0 | - |
| 3.0508 | 24150 | 0.0 | - |
| 3.0571 | 24200 | 0.0 | - |
| 3.0634 | 24250 | 0.0 | - |
| 3.0697 | 24300 | 0.0 | - |
| 3.0760 | 24350 | 0.0 | - |
| 3.0824 | 24400 | 0.0 | - |
| 3.0887 | 24450 | 0.0 | - |
| 3.0950 | 24500 | 0.0 | - |
| 3.1013 | 24550 | 0.0 | - |
| 3.1076 | 24600 | 0.0 | - |
| 3.1139 | 24650 | 0.0 | - |
| 3.1203 | 24700 | 0.0 | - |
| 3.1266 | 24750 | 0.0 | - |
| 3.1329 | 24800 | 0.0 | - |
| 3.1392 | 24850 | 0.0 | - |
| 3.1455 | 24900 | 0.0 | - |
| 3.1518 | 24950 | 0.0 | - |
| 3.1582 | 25000 | 0.0 | - |
| 3.1645 | 25050 | 0.0 | - |
| 3.1708 | 25100 | 0.0 | - |
| 3.1771 | 25150 | 0.0 | - |
| 3.1834 | 25200 | 0.0 | - |
| 3.1897 | 25250 | 0.0 | - |
| 3.1961 | 25300 | 0.0 | - |
| 3.2024 | 25350 | 0.0 | - |
| 3.2087 | 25400 | 0.0 | - |
| 3.2150 | 25450 | 0.0 | - |
| 3.2213 | 25500 | 0.0 | - |
| 3.2276 | 25550 | 0.0 | - |
| 3.2340 | 25600 | 0.0 | - |
| 3.2403 | 25650 | 0.0 | - |
| 3.2466 | 25700 | 0.0 | - |
| 3.2529 | 25750 | 0.0 | - |
| 3.2592 | 25800 | 0.0 | - |
| 3.2655 | 25850 | 0.0 | - |
| 3.2719 | 25900 | 0.0 | - |
| 3.2782 | 25950 | 0.0 | - |
| 3.2845 | 26000 | 0.0 | - |
| 3.2908 | 26050 | 0.0 | - |
| 3.2971 | 26100 | 0.0 | - |
| 3.3034 | 26150 | 0.0 | - |
| 3.3098 | 26200 | 0.0 | - |
| 3.3161 | 26250 | 0.0 | - |
| 3.3224 | 26300 | 0.0 | - |
| 3.3287 | 26350 | 0.0 | - |
| 3.3350 | 26400 | 0.0 | - |
| 3.3413 | 26450 | 0.0 | - |
| 3.3477 | 26500 | 0.0 | - |
| 3.3540 | 26550 | 0.0 | - |
| 3.3603 | 26600 | 0.0 | - |
| 3.3666 | 26650 | 0.0 | - |
| 3.3729 | 26700 | 0.0 | - |
| 3.3792 | 26750 | 0.0 | - |
| 3.3855 | 26800 | 0.0 | - |
| 3.3919 | 26850 | 0.0 | - |
| 3.3982 | 26900 | 0.0 | - |
| 3.4045 | 26950 | 0.0 | - |
| 3.4108 | 27000 | 0.0 | - |
| 3.4171 | 27050 | 0.0 | - |
| 3.4234 | 27100 | 0.0 | - |
| 3.4298 | 27150 | 0.0 | - |
| 3.4361 | 27200 | 0.0 | - |
| 3.4424 | 27250 | 0.0 | - |
| 3.4487 | 27300 | 0.0 | - |
| 3.4550 | 27350 | 0.0 | - |
| 3.4613 | 27400 | 0.0 | - |
| 3.4677 | 27450 | 0.0 | - |
| 3.4740 | 27500 | 0.0 | - |
| 3.4803 | 27550 | 0.0 | - |
| 3.4866 | 27600 | 0.0 | - |
| 3.4929 | 27650 | 0.0 | - |
| 3.4992 | 27700 | 0.0 | - |
| 3.5056 | 27750 | 0.0 | - |
| 3.5119 | 27800 | 0.0 | - |
| 3.5182 | 27850 | 0.0 | - |
| 3.5245 | 27900 | 0.0 | - |
| 3.5308 | 27950 | 0.0 | - |
| 3.5371 | 28000 | 0.0 | - |
| 3.5435 | 28050 | 0.0 | - |
| 3.5498 | 28100 | 0.0 | - |
| 3.5561 | 28150 | 0.0 | - |
| 3.5624 | 28200 | 0.0 | - |
| 3.5687 | 28250 | 0.0 | - |
| 3.5750 | 28300 | 0.0 | - |
| 3.5814 | 28350 | 0.0 | - |
| 3.5877 | 28400 | 0.0 | - |
| 3.5940 | 28450 | 0.0 | - |
| 3.6003 | 28500 | 0.0 | - |
| 3.6066 | 28550 | 0.0 | - |
| 3.6129 | 28600 | 0.0 | - |
| 3.6193 | 28650 | 0.0 | - |
| 3.6256 | 28700 | 0.0 | - |
| 3.6319 | 28750 | 0.0 | - |
| 3.6382 | 28800 | 0.0 | - |
| 3.6445 | 28850 | 0.0 | - |
| 3.6508 | 28900 | 0.0 | - |
| 3.6572 | 28950 | 0.0 | - |
| 3.6635 | 29000 | 0.0 | - |
| 3.6698 | 29050 | 0.0 | - |
| 3.6761 | 29100 | 0.0 | - |
| 3.6824 | 29150 | 0.0 | - |
| 3.6887 | 29200 | 0.0 | - |
| 3.6950 | 29250 | 0.0 | - |
| 3.7014 | 29300 | 0.0 | - |
| 3.7077 | 29350 | 0.0 | - |
| 3.7140 | 29400 | 0.0 | - |
| 3.7203 | 29450 | 0.0 | - |
| 3.7266 | 29500 | 0.0 | - |
| 3.7329 | 29550 | 0.0 | - |
| 3.7393 | 29600 | 0.0 | - |
| 3.7456 | 29650 | 0.0 | - |
| 3.7519 | 29700 | 0.0 | - |
| 3.7582 | 29750 | 0.0 | - |
| 3.7645 | 29800 | 0.0 | - |
| 3.7708 | 29850 | 0.0 | - |
| 3.7772 | 29900 | 0.0 | - |
| 3.7835 | 29950 | 0.0 | - |
| 3.7898 | 30000 | 0.0 | - |
| 3.7961 | 30050 | 0.0 | - |
| 3.8024 | 30100 | 0.0 | - |
| 3.8087 | 30150 | 0.0 | - |
| 3.8151 | 30200 | 0.0 | - |
| 3.8214 | 30250 | 0.0 | - |
| 3.8277 | 30300 | 0.0 | - |
| 3.8340 | 30350 | 0.0 | - |
| 3.8403 | 30400 | 0.0 | - |
| 3.8466 | 30450 | 0.0 | - |
| 3.8530 | 30500 | 0.0 | - |
| 3.8593 | 30550 | 0.0 | - |
| 3.8656 | 30600 | 0.0 | - |
| 3.8719 | 30650 | 0.0 | - |
| 3.8782 | 30700 | 0.0 | - |
| 3.8845 | 30750 | 0.0 | - |
| 3.8909 | 30800 | 0.0 | - |
| 3.8972 | 30850 | 0.0 | - |
| 3.9035 | 30900 | 0.0 | - |
| 3.9098 | 30950 | 0.0 | - |
| 3.9161 | 31000 | 0.0 | - |
| 3.9224 | 31050 | 0.0 | - |
| 3.9288 | 31100 | 0.0 | - |
| 3.9351 | 31150 | 0.0 | - |
| 3.9414 | 31200 | 0.0 | - |
| 3.9477 | 31250 | 0.0 | - |
| 3.9540 | 31300 | 0.0 | - |
| 3.9603 | 31350 | 0.0 | - |
| 3.9666 | 31400 | 0.0 | - |
| 3.9730 | 31450 | 0.0 | - |
| 3.9793 | 31500 | 0.0 | - |
| 3.9856 | 31550 | 0.0 | - |
| 3.9919 | 31600 | 0.0 | - |
| 3.9982 | 31650 | 0.0 | - |
| 4.0 | 31664 | - | 0.0117 |
* The bold row denotes the saved checkpoint.
### Framework Versions
- Python: 3.9.18
- SetFit: 1.0.3
- Sentence Transformers: 2.2.1
- Transformers: 4.32.1
- PyTorch: 1.10.0
- Datasets: 2.20.0
- Tokenizers: 0.13.3
## Citation
### BibTeX
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
doi = {10.48550/ARXIV.2209.11055},
url = {https://arxiv.org/abs/2209.11055},
author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Efficient Few-Shot Learning Without Prompts},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->